CA2447512A1 - Method and apparatus for evaluating fraud risk in an electronic commerce transaction - Google Patents

Method and apparatus for evaluating fraud risk in an electronic commerce transaction Download PDF

Info

Publication number
CA2447512A1
CA2447512A1 CA002447512A CA2447512A CA2447512A1 CA 2447512 A1 CA2447512 A1 CA 2447512A1 CA 002447512 A CA002447512 A CA 002447512A CA 2447512 A CA2447512 A CA 2447512A CA 2447512 A1 CA2447512 A1 CA 2447512A1
Authority
CA
Canada
Prior art keywords
risk
fraud
transaction
fraud risk
estimates
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
CA002447512A
Other languages
French (fr)
Inventor
William Wright
Hung-Tzaw Hu
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CyberSource Corp
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Publication of CA2447512A1 publication Critical patent/CA2447512A1/en
Abandoned legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/38Payment protocols; Details thereof
    • G06Q20/40Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/04Payment circuits
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/08Payment architectures
    • G06Q20/10Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/38Payment protocols; Details thereof
    • G06Q20/40Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401Transaction verification
    • G06Q20/4016Transaction verification involving fraud or risk level assessment in transaction processing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/38Payment protocols; Details thereof
    • G06Q20/40Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/403Solvency checks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0609Buyer or seller confidence or verification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03Credit; Loans; Processing thereof
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08Insurance
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07FCOIN-FREED OR LIKE APPARATUS
    • G07F7/00Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus
    • G07F7/08Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by coded identity card or credit card or other personal identification means

Abstract

In an e-commerce risk screening system (900), transaction information is applied to multiple fraud risk models (915, 916, 918, 920) that produce raw scores, which are transformed with sigmoidal transform functions (910) to produce optimized likelihood of fraud risk estimates. Such estimates are combined using fusion proportions, producing a single point risk estimate, which is transformed with a sigmoidal function (910) to produce an optimized single point risk estimate.

Description

METHOD AND APPARATUS FOR EVALUATING FRAUD RISK IN AN
ELECTRONIC COMMERCE TRANSACTION
CROSS REFERENCE TO RELATED APPLICATIONS
This application claims priority from U.S. Provisional Patent Application No.
60/294,852 filed May 30, 2001, entitled "Method and Apparatus for Evaluating Fraud Risk in an Electronic Commerce Transaction Providing Dynamic Self Adjusting Multi-Source Adversarial Risk Likelihood Tracking," which is hereby incorporated by reference in its entirety, as if fully set forth herein, for all purposes.
FIELD OF THE INVENTION
The present invention relates generally to electronic commerce transaction processing and, more specifically, to techniques for evaluating fraud rislc in an electronic commerce transaction.
BACKGROUND OF THE INVENTION
Any business that accepts bank or credit cards for payment accepts some amount of risk that the transaction is fraudulent. However, for most merchants the benefits of accepting credit cards outweigh the risks. Conventional "brick and mortar"
merchants, as well as mail order and telephone order merchants, have enjoyed years of business expansion resulting from credit card acceptance, supported by industry safeguards and services that are designed to contain and control the risk of fraud.
Credit card transactions are being utilized in a variety of environments. In a typical environment a customer, purchaser or other user provides a merchant with a credit card, and the merchant through various means will verify whether that information is accurate. In one approach, credit card authorization is used. Generally, credit card authorization involves contacting the issuer of the credit card or its agent, typically a bank or a national credit card association, and receiving information about whether or not funds (or credit) are available for payment and whether or not the card number is valid. If the card has not been reported stolen and funds are available, the transaction is authorized.
This process results in an automated response to the merchant of "Issuer Approved" or "Issuer Denied." If the merchant has received a credit card number in a "card not present" transaction, such as a telephone order or mail order, then the credit card authorization service is often augmented by other systems, but this is the responsibility of the individual merchant. , Fox example, referring now to FIG. 1, a typical credit card verification system 100 is shown. In such a system, a merchant 102 receives a credit card from the customer 104.
The merchant then verifies the credit card information through an automated address verification system ("AVS") 106. These systems work well in a credit card transaction in which either the customer has a face-to-face meeting with the merchant or the merchant is actually shipping merchandise to the customer's address.
The verification procedure typically includes receiving at the AVS 106 address information and identity information. AVS 106 is currently beneficial for supporting the screening of purchases made by credit card customers of certain banks in the United States. In essence, the bank that issues a credit card from either of the two major brands (Visa or MasterCard) opts whether or not to support the AVS 106 procedure. The AVS
check, designed to support mail order and telephone order businesses, is usually run in conjunction with the credit card authorization request. AVS 106 performs an additional check, beyond verifying funds and credit card status, to ensure that elements of the address supplied by the purchaser match those on record with the issuing bailk. When a merchant executes an AVS check, the merchant can receive the following responses:
AVS=MATCH-The first four numeric digits of the street address, the first five numeric digits of the ZIP code, and the credit card number match those on record at the bank;
AVS=PARTIAL MATCH-There is a partial match (e.g., street matches but not ZIP code, or ZIP code matches but not street);
AVS=UNAVAB,ABLE-The system cannot provide a response. This result is returned if the system is down, or the bank card issuer does not support AVS, or the bank card issuer for the credit card used to purchase does not reside in the United States;
AVS=NON-MATCH-There is no match between either the address or ZIP data elements.
While most merchants will not accept orders that result in a response of "Issuer Denied" or "AVS NON-MATCH," the automated nature of an online transaction requires merchants to implement policies and procedures that can handle instances where the card has been approved, but other data to validate a transaction is questionable. Such instances include cases where the authorization response is "Issuer Approved,"
but the AVS response is AVS=PARTIAL MATCH, AVS=UNAVAILABLE, or even AVS=MATCH. Thus, the purchaser's bank may approve the transaction, but it is not clear whether the transaction is valid.
_2_ Because significant amounts of legitimate sales are associated with AVS
responses representing unknown levels of risk (or purchases made outside of the United States where AVS does not apply), it is critical to find ways to maximize valid order acceptance with the lowest possible risk. Categorically denying such orders negatively impacts sales and customer satisfaction, while blind acceptance increases risk. Further, even AVS=MATCH responses Cathy some riskbecause stolen card and address information can prompt the AVS=MATCH response.
To address these issues, merchants have augmented card authorization and AVS
results with additional screening procedures and systems. One such additional procedure is to manually screen orders. While this approach is somewhat effective when order volume is low, the approach is inefficient and adds operating overhead that cannot scale with the business.
ELECTROI~IIC COMMERCE
Electronic commerce or online commerce is a rapidly expanding field of retail and business-to-business commerce. In electronic commerce, a buyer or purchaser normally acquires tangible goods or digital goods or services from a merchant or the merchant's agent, in exchange for value that is transferred from the purchaser to the merchant.
Electronic commerce over a public network such as the Internet offers an equal or greater business opportunity than conventional, brick-and-mortar business, but requires special precautions to ensure safe business operations. The technological foundation that makes e-shopping compelling-e.g., unconstrained store access, anonymity, shopping speed, and convenience-also provides new ways for thieves, or "fraudsters", to commit credit card fraud.
When a transaction involves transmitting information from an online service or the Internet, address and identity information are not enough to confidently verify that the customer who is purchasing the goods is actually the owner of the credit card.
For example, an individual may have both the name and the address of a particular credit card holder and that information in a normal transaction may be sufficient for authorization of such a transaction. However, in an Internet transaction it is possible to obtain all the correct information related to the particular credit card holder through unscrupulous means, and therefore, carry out a fraudulent transaction.
Accordingly, what is needed is a system and method that overcomes the problems associated with a typical verification system for credit card transactions, particularly in the Internet or online services environment. The system should be easily implemented within the existing environment and should also be straightforwardly applied to existing technology.
While not all merchants experience fraud, as it is highly dependent on the nature of the business and products sold, in one study the aggregate risk of fraud was found to range between 4% and 23% of authorized sales transacted, depending upon the lenience of the merchant's acceptance criteria. Because Internet transactions are classified as "Card Not Present" transactions under the operating rules of the major credit card associations, in most cases Internet merchants are liable for a transaction even if the acquiring bank has authorized the transaction. As a result, fraud has a direct and immediate impact on the online merchant.
Electronic connnerce fraud is believed to be based largely on identity theft rather than stolen cards. Generally, in electronic commerce fraud that is based on identity theft, the legitimate cardholder does not detect or know that the identifying information or credit card account is being used illegally, until the cardholder reviews a monthly statement and finds fraudulent transactions. In contrast, in a stolen card case, the cardholder has lost possession of the card itself and usually notifies credit card company officials or law enforcement immediately. As a result, the impact of fraud is different in the electronic commerce context; it affects a merchant's operating efficiency, and possibly the merchant's discount rate and ability to accept credit cards.
In one approach, online merchants attempt to avoid this risk by declining all but the safest orders or by instituting manual screening methods. However, merchants using these approaches generally suffer business inefficiency and lost sales. These merchants turn away a significant portion of orders that could have been converted to sales, increase overhead costs, and limit business scalability. Thus both fraud and overly stringent methods or non-automated methods of protecting the business from fraud can negatively impact business operations.
Although risk-susceptible transactions can be tested in a variety of ways for risk indications, none of the resulting risk test outcomes, alone, are sufficient for determining whether the transaction should be accepted or rejected. Each test outcome must be assigned a numeric value or a weighting factor as a component of the overall transaction risk. These components must be combined and the resulting combination risk estimate transformed into a single numeric indicator which can then be used to determine whether the transaction is to be accepted for further processing or reviewed for possible rejection.
In this context, numerous issues deserve attention, concerning:
How the individual test outcome penalties are best determined;
2. How the individual test outcome penalties are best combined;
3. How the resulting combination of test outcome penalties should best be shaped or transformed to optimally serve the needs of the decision domain;
4. How more than one such decision-domain-tailored risk estimate or score should be optimally combined through multi-source fusion to create the best single point estimate of risk likelihood; and 5. How to modify that optimal point estimate so that it does not violate the expectations of legacy system users beyond a reasonable limit.
MATHEMATICAL MODELING
Mathematical models are developed in an attempt to approximate the behavior of real-world processes, situations, or entities (hereinafter addressed solely as a "process,"
for purposes of simplicity and clarity, not for purposes of limitation). A
model may be as accurate as it can be at a moment in time, but if the process that is being modeled is changing over time, a static model is likely to diverge from the real-world process that it is attempting to model. Hence, the ability of a static model to predict a real-world result degrades as a result of this divergence.
Dynamic models are developed and deployed to overcome the likelihood and rate of divergence between the model and the process that the model is approximating by attempting to adjust to the changes occurring to the underlying process.
Often, models are adjusted in response to some form of feedback representing the changes to the underlying process; at times by adjusting parameters within the model.
A process that is being modeled is adversarial if it is "aware" that it is being modeled and does not want to be modeled. In a sense, the process is actively changed in order to undermine the accuracy and performance of the model being used to predict its behavior. In the domain of fraud risk likelihood tracking, fraudsters are actively trying to undermine the predictive model in order to continue their fraudulent activities, by changing their process.
Based on the foregoing, there is a clear need for an improved method and system for determining a fraud risk associated with an electronic commerce transaction that addresses the foregoing issues.
There is a need for a way to assist merchants in screening fraudulent Internet transactions by calculating and delivering a risk score in real time.
There is also a need for a way to detect a fraud risk associated with an electronic commerce transaction that is based on criteria unique to or specific to the electronic commerce environment and attuned to the kinds of attempts at fraud that are perpetrated by prospective buyers.
There is a specific need for a way to determine a fraud risk associated with an electronic commerce transaction that is useful in a computer-based merchant services system.
SUMMARY OF THE INVENTION
Mechanisms are provided for evaluating the risk of fraud in an electronic transaction. According to one aspect, transaction information from a transaction is received and applied to multiple fraud risk mathematical models that each produce a respective raw score, and the raw scores are transformed with respective sigmoidal transform functions to produce respective optimized likelihood of fraud risk estimates. In one embodiment, the respective risk estimates are combined using fusion proportions associated with the respective risk estimates, producing a single point risk estimate for the transaction, and the single point risk estimate is transformed with a sigmoidal function to produce an optimized single point risk estimate for the transaction.
The sigmoidal functions are derived, according to one embodiment, to approximate an observed relationship between risk estimates produced by fraud risk detection models and a percentage of transactions associated with respective risk estimates, where the relationship is represented in terms of real-world fraudulent transaction and non-fraudulent transaction distributions. In an additional embodiment, the sigmoidal functions are derived by constraining the respective functions to the abscissas of the following three inflection points: (1) a first point, at which the slope of the fraudulent transaction distribution becomes mathematically trivial in proximity to zero percentage transactions; (2) a second point, at which the slope of the non-fraudulent transaction distribution becomes mathematically trivial in proximity to zero percentage transactions; and (3) a third point, at which the fraudulent and non-fraudulent transaction distributions intersect.
In one embodiment, derivations of the sigmoidal functions are controlled such that they are dynamically adjustable based on the change to the observed relationship represented by the real-world transaction distributions. Each inflection point determines a defining transition point on the mapping between a raw score and its sigmoidal transformation as follows: (1) the first inflection point determines where the sigmoidal transfer function enters the transition from low to medium risk. (2) the second inflection point determines where the sigmoidal transfer function surface transitions from concave to convex, corresponding to the maximally confusable mid range of risk, and (3) the third inflection point determines where the sigmoidal transfer function transitions from medium to high risk.
One embodiment is directed to computing respective risk test penalties for multiple risk tests for one or more of the multiple fraud risk mathematical models that are used to estimate the likelihood of fraud, given a certain pattern of events represented by the transaction information. The respective risk test penalties are computed as the inverse of the sum of one and a false positive ratio for the respective risk test. In another embodiment, a weighted summation of the respective risk test penalties is computed to produce the raw score from the associated model for the transaction.
Various implementations of the techniques described are embodied in methods, systems, apparatus, and in computer-readable media.
BRIEF DESCRIPTION OF THE DRAWITTGS
The present invention is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar elements and in which:
FIG. 1 is a block diagram illustrating a typical credit card verification system;
FIG. 2 is a block diagram illustrating a system that would use the verification procedure in accordance with the present invention;
FIG. 3 is a block diagram illustrating an integrated verification of a credit card transaction over the Internet;
FIG. 4 is a block diagram illustrating a statistical modeling process;
FIG. 5 is a graph illustrating two frequency distributions: the score distribution of Good Transactions and that of Bad Transactions;
FIG. 6 is a graph illustrating a Limit Surface established below the Heuristic Score Surface to help minimize the likelihood of Type I Errors and a Limit Surface established above the Heuristic Score Surface to help minimize the likelihood of Type II
Errors;
FIG. 7 is a graph illustrating possible outcomes from a classical fraud detection risk assessment;
FIG. 8 is a graph illustrating a mapping of a sigmoidal transform surface onto the decision domain;
FIG. 9 is a block diagram illustrating an example transaction risk assessment system;

FIG. 10A is a block diagram illustrating a general fraud screening system, in which embodiments of the invention may be implemented;
FIG. 1 OB is a block diagram illustrating a transaction verification system that may be used to implement fraud screening and risk scoring system;
FIG. 11 is a block diagram illustrating an example embodiment of a gibberish test;
FIG. 12A is a flow diagram illustrating a process of applying a geo-location test based on area code;
FIG. 12B is a flow diagram illustrating a process of applying a geo-location test based on email address;
a FIG. 12C is a flow diagram illustrates a process of applying a geo-location test based upon bank identification number;
FIG. 13 is a block diagram illustrating alternative embodiments of an Internet identity value system; and FIG. 14 is a block diagram illustrating a computer system upon which an embodiment of the invention may be implemented.
DETAILED DESCRIPTION
A method and apparatus are described fox evaluating fraud risk in an electronic commerce transaction. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, that the present invention may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to avoid urmecessarily obscuring the present invention. Various modifications to the described embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. Thus, the present invention is not intended to be limited to the embodiment shown but is to be accorded the widest scope consistent with the principles and features described herein.
FRAUD DETECTION SYSTEM-GENERAL
The present invention may operate in an integrated verification system for credit card transactions over an online service or the Internet. FIG. 2 is a block diagram of a system 200 which uses verification as described herein. System 200 includes, similar to FIG. 1, a customer 102 and a merchant 104. The customer 102 provides the merchant with credit card and other pertinent information (e.g., customer's e-mail address), and the _g_ merchant then sends the information to an integrated verification system ("IVS") 206, to determine whether the credit card information is valid. The IVS 206 is typically implemented in software, for example on a hard disk, floppy disk or other computer-readable medium.
Different verification parameters that the IVS 206 utilizes are typically weighted relative to the particular credit card transaction. For example, if the amount of dollar transaction is critical, it may be appropriate to weight a history check (for verifying the history of transactions associated with the particular credit card information) and an AVS system check more critically than other parameters. On the other hand, if a critical point is the consistency of the Internet address, then a consistency check (for verifying consistency of the credit card information) and an Internet identification system (for verifying validity of Internet addresses) may be more critical. Accordingly, each of the verification parameters may be weighted differently depending upon its importance in the overall transaction verification process to provide a merchant with an accurate quantifiable indication as to whether the transaction is fraudulent.
FIG. 3 shows a simple block diagram for providing an integrated verification of a credit card transaction over the Internet. The IVS 206 (FIG. 2) includes a controller 312 that receives the credit information from the merchant and then sends that information on to a variety of parameters 302-308. The plurality of parameters operate on the information to provide an indication of whether the transaction is valid. In this embodiment, the plurality of parameters comprises a history check 302, a consistency check 304, an automatic verification system 306 and an Internet identification verification system ("IIVS") 308. The output or individual indications of validity of these parameters are provided to fraud detector 310. The fraud detector 310 combines these inputs to provide an integrated indication of whether the particular transaction is valid.
Consistency check 304 allows IVS 206 to determine whether the credit information is consistent, i.e., does the credit information match the user and other information. AVS system 306 provides similar information as does AVS 106 as described in reference to FIG. 1. A key feature of both the history database 322 and the W ternet lD database 324 is that they can be accessed and the information there within can be supplemented by a variety of other merchants and, therefore, information from those merchants is obtainable thereby.
History check 302 is provided which also accesses a history database 322 which may include card number and email information. The history check 302 will also actively determine if the particular transaction matches previous database information _9_ within the history database 322. Therefore, the Internet ID verification system 308 and history check 302 increases in utility over time. The Internet ID verification system 308 provides for a system for verifying the validity of an Internet address, the details of which will be discussed hereinafter. The Internet identification verification system 308 similar to the lustory check 302 includes a database 324 which can be supplemented by other merchants. In addition, the Internet identification verification system 308 accesses and communicates with a database of Internet addresses. This system will be used to verify whether the Internet address is consistent with other Internet addresses being used in transactions utilizing this credit card.
FRAUD RISK MATHEMATICAL MODELS
1. STATISTICAL MODELING
A statistical model (such as statistical model 1040 of FIG. l OB) comprises a plurality of computations that are based upon actual discrete scores that are weighted in non-linear combination, based on likelihood of indicating an actual fraudulent transaction.
In one embodiment, such weighting involves identifying orders that are actually consummated and that result in actual charge-backs to the issuing bank associated with the credit card that is identified in the order. The methodology generally ignores orders that are rejected by the fraud screening system disclosed herein as part of the transaction present tests 1010 of FIG. 10B.
FIG. 4 is a block diagram of a statistical modeling process. In one embodiment, statistical modeling consists of a data selection and sampling phase 402, data normalization phase 404, data partitioning phase 406, model training phase 410, model verification phase 412, and model performance testing phase 418. Many of these phases can contribute feedback to earlier phases, as indicated by paths in FIG. 4.
A. DATA SELECTION AND SAMPLING
In general, phase 402 of the statistical modeling process consists of data selection and sampling. The word "data", in this context, refers to truth-marked transaction data.
"Truth-marked" means that the transaction records include a field indicating the final outcome of the transaction - whether the transaction ultimately resulted in an adverse outcome such as chargeback or suspicious credit back, or the transaction resulted in a good sale. During this phase the sources of truth-marked modeling data are selected. If the model is to provide custom protection to a single merchant, then data specific to that merchant would dominate but the modeling set might also contain representative data from similar merchants as well to broaden the modeling basis. If the model were to serve an entire industry sector then the data would be chosen broadly to represent the sector merchants. However broad the applicability of the model, the data selection is equally broad.
However, this transaction data is not used for statistical modeling as-is; it is down-sampled. Down-sampling is a statistical process by which the modeler achieves an optimal balance between high-risk and low-risk transactions in the modeling set through biased random sampling. The modeler establishes the optimal mix proportions based on theoretical characteristics of the model that is to be built. Fox example, in many cases, high-risk transactions are rare in relation to low-risk. If the selected data is used for modeling as-is, the low-risk transactions could dominate and drown out the signal from the infrequent high-risk items. A balance is desirable. Typically, a ten-to-one ratio of low-risk to high-risk data items is obtained, by accepting all high-risk items in the selected data set and then randomly down-sampling the low-risk items, to achieve the desired ratio.
B. DATA NORMALIZATION
Statistical modeling schemes typically respond best to data that are numerically well-behaved. Since transaction data and test result data can, in principle, contain values from all across the numeric spectrum, the data are normalized by applying the statistical Z-transform or some other such transform to achieve equal interval measurement across models and to fit all data values into a specified range, such as from minus one to plus' one, or less optimally from zero to one. This makes the modeling task more stable and the results more robust. These functions are carried out in data normalization phase 404.
C. DATA PARTITIONING
In data partitioning phase 406, the selected and sampled data is broken down into three partitions or mutually exclusive data sets: a training set, a verification set, and a testing set. Although there is no required proportion for these data sets, proportions such as 50-50 and 60-40 are commonly used. For example, using the 60-40 proportion, percent of the modeling data is randomly chosen for training and validation, and the remaining 40 percent is held aside or held back as testing data for the model testing phase. The 60 percent chosen for model building is further broken down according to another rule of thumb such as 65-35 into training data and validation data, both of which participate in a model building phase 408. All partitioning is done using pseudo-random number generation algorithms.
D. MODEL TRAINING
' Once the modeling data are selected, sampled, normalized, and partitioned, model training phase 410 is carried out. The first step is to select or create an initial candidate model architecture. For non-linear statistical models such as neural networks and basis function networks, this involves configuring the input layer to conform to the dimensionality of the modeling data feature set, configuring the output layer to conform to the demands of the model domain, and then selecting an initial number of "hidden units" or "basis function units". If the demands of the model domain are to make a simple numeric estimation of the transaction risk, then a single unit output architecture is chosen. If the modeling domain demands that the transaction be categorized into multiple risk type estimates, then the output layer is made to conform to the dimensionality of the target category set.
With each successive training cycle, the model is exposed to the training data one transaction at a time and allowed to self adjust the model weights attempting to achieve a "best balance" in the face of the entire data set - a balance between correct risk estimation for the low-risk transactions and correct risk estimation for the high-risk transactions.
The training cycle is terminated when the rate of successful weight adjustment, as measured by successive improvements in mean square error, begins to asymptote or flatten out. Training beyond that point may result in "over-fit" where the model becomes so specifically conditioned to the training data that later, in the performance testing phase, it will fail to generalize to previously unseen but similar patterns of data.
If the model fails to train to criteria, then the modeler returns to one of the previous steps and enters the modeling cycle again, adjusting to prevent the modeling failure on the next cycle.
The most common step for modeling entry is to return to the beginning of the model-training phase and make adjustments to the architecture, although it is not uncommon to go back to the data selection and sampling phase if necessary.
E. MODEL VERIFICATION
The model-in-training, or the completely trained model, or both, are subjected to verification in model verification phase 412. During this phase the behavior of the model is checked against common sense criteria by bringing some of the verification data to bear on the model. In a way this is an interim form of performance testing. The difference is that, once adjustments are made to the model, the verification data that was used to determine the nature ,of the required model change becomes part of the ongoing training set. Typically, after a cycle of verification reveals some model weakness, the modeling process is re-entered at one of the earlier stages. This cycling between model training phase 410, model verification phase 412, model adjustment, and model re-training concludes the general model building phase 40~.
F. MODEL TESTING
Once model building cycles have completed, the finished model is subjected to model performance testing in testing phase 416. The 40-50 percent of the original selected and sampled data that was held back for performance testing is now brought to bear. The model has never been exposed to this trmsaction data before. The model scores all of the remaining data, without allowing any modifications to be made to its weights or architecture. The results of scoring are analyzed. If the model has performed to criteria, modeling is completed and the statistical model is ready for deployment in the production fraud risk estimation system where it will be exposed to transactions as they are presented to the system in real time and produce a muneric risk estimate for each transaction. That numeric risk estimate can be interpreted as fraud likelihood, the likelihood that the transaction will turn out to be bad.
If the model does not perform to criteria, the modeling process begins again from the beginning with a new data selection and sampling cycle, as shown in FIG.
4. This renewed modeling process can be used to extend the under-performing model or to begin a new model, incorporating lessons learned during the previous modeling cycles.
2. HEURISTIC MODELING
A heuristic model (such as Heuristic Model 1050 of FIG. l OB) is comprised of one or more artificial intelligence computations that compute a weighted sum based on a linear combination of the discrete scores generated by other models or tests.
The heuristic computations are performed on the results of the heuristic tests.
This is a highly complex scoring process that occurs in stages and results in a single numeric estimation of risk. This risk estimate can then serve as the basis for a score blending process (such as Score Blending Process 1052 of FIG. l OB), establishing the Risk Zones that structure the blending process. This blending process is discussed in detail below.
Initially, a total raw score is computed as the weighted sum of the discrete test results. Discrete test results are of four types: Boolean, quantitative, categorical, and probabilistic. Boolean true-false results are valued at zero or one.
Quantitative results are valued as positive integers reflecting arithmetic counts of occurrence or magnitude.
Categorical results indicate discrete categories of information related to levels of risk severity. Probabilistic results indicate levels of estimation confidence pertaining to uncertain risk indicators. Each discrete test result is multiplied by an associated penalty value, and these products are summed together to produce the total raw score.
The penalty associated with each test can be negative or positive. Negative penalties reduce the likelihood of risk and positive penalties increase the risk likelihood.
The resulting total raw score indicates the face value and situational risk of the transaction.
Next, the heuristic model computes a raw score multiplier. The raw score multiplier is similar to a "gain control" device. The raw score is boosted upward or reduced based on a combination of certain test results and the merchant's declared policy toward those test results. If the merchant has indicated a special interest in a particular test, then the results of that test are magnified to boost the score upward or downward -mostly upward. Based on the merchant preferences for specified tests, and on those test results, a score multiplier is computed and applied to the total raw score resulting in a "classic" score. The resulting classic score ranges in value from 0 to a very large number which can be greater than 100,000 and in its upper ranges appear to be sparsely distributed exponentially.
Finally, the classic score is scaled and transformed into a non-linear bounded estimate of the likelihood of transaction risk by sigmoidally superimposing the raw score distribution onto the inflection points of the underlying decision domain.
This Heuristic Model score ranges from 0 to 99 and is an estimate of risk likelihood. This heuristic estimate is later combined with the results of other models through a process of numeric fusion described below.
3. RISK ESTIMATE BLENDING
All risk likelihood estimates derived from the heuristic, statistical, and other models can be sigmoidally transformed (as described above) and then blended or fused to produce a final comprehensive estimate of the likelihood of risk associated with the transaction-merchant-card-fraudster combination. This is commonly called the Fraud Score, and is called the Risk Estimate herein. The blending (described in more detail below under the heading "Multi-Source Diagnostic Fusion Component") is carned out using certain values derived from analyzing transaction distributions, which are illustrated in FIG. 5. For illustrating the process of risk estimate fusion, a two model example will be presented consisting of a heuristic model and a statistical model.
FIG. 5 shows two frequency distributions: the score distribution of Good Transactions and that of Bad Transactions. By overlaying the distribution of Risk Estimates observed for truly bad transactions on the distribution of truly good transactions, four Risk Zones are established. Risk Zone 1 begins at the lowest risk likelihood (Risk Score 0) and extends to the first inflection point where the occurrence of fraud transactions becomes non-trivial. Risk Zone 1 contains low-scoring transactions that are highly unlikely to be fraudulent.
Referring again to FIG. 5, Risk Zone 2 begins in the general non-fraud zone at the first inflection point where the occurrence of fraud transactions becomes non-trivial and extends to the second inflection point, which is the intersection of the Good Transactions frequency surface and the Bad Transactions frequency surface. That boundary is also defined as Error Minimization (EM) point, tile point that balances the risk of Type I and Type II Error and is traditionally recommended as a default discrete decision threshold.
Risk Zone 2 contains mostly non-fraudulent transactions but also a mix of mid-low scoring fraudulent transactions. Type II Errors (also known as Misses, Missed Detections, Mistaken Sales, and Fraud Losses) occur when fraudulent transactions score in Risk Zones 1 and 2 and are thus mistakenly accepted for processing.
Risk Zone 3 of FIG. 5 begins at the default Error Minimization second inflection point and extends to the third inflection point in the general fraud zone where the occurrence of non-fraudulent transactions becomes trivial. Risk Zone 3 contains mostly fraudulent transactions but also a mix of mid-high scoring non-fraudulent transactions.
Risk Zone 4 begins at the third inflection point where the occurrence of mid-high scoring non-fraudulent transactions becomes trivial and extends to the top of the scoring range.
Risk Zone 4 contains high-scoring transactions that are extremely likely to be fraudulent.
Type I Errors (also known as False Alarms, False Positives, Mistaken Non-Sales, and Lost Business Opportunities) occur when non-fraudulent transactions score in Risk Zones 3 and 4 and are thus mistakenly rejected from processing.
According to one embodiment, the score value (Risk Estimate) of statistical models and heuristic models are blended in a score blending process, generally as follows. For each of the four Risk Zones, a blending policy is established and enforced, dictating the magnitude and the allowable direction of influence the models are permitted.
The policies are a function of both the nature of the risk estimation algorithms yielding the scores being blended, and the nature of the Risk Zones themselves.

In one embodiment, the Heuristic Model is taken as the basic scoring authority for establishing the boundaries of all Risk Zones. In this embodiment, a Statistical Model is intended primarily to protect non-fraudulent transactions from mistakenly receiving a high Risk Estimation (to prevention of False Alarms), and since most non-fraudulent transactions naturally fall in Risk Zones 1 and 2, the Statistical Model is given increased responsibility for reducing Risk Estimations in Zone l and limited authority to reduce Risk Estimations in Zone 2. Further, in this example embodiment, since the Heuristic Model is intended primarily to optimize the detection of fraudulent transactions (and thus to avoid Misses); and since most fraudulent transactions naturally fall in Zones 3 and 4, that model is given full responsibility for producing Risk Estimates in Zone 4 and primary responsibility for producing Risk Estimates in Risk Zone 3. The Statistical Model is then given limited authority to decrease certain Risk Estimates in Zone 3.
W another embodiment, the Heuristic Model is taken as the basic scoring authority for establishing the boundaries of all Risk Zones. In this embodiment, a Statistical Model is intended primarily to prevent fraudulent transactions from mistakenly receiving a low Risk Estimation (for prevention of Missed Detections). Since most fraudulent transactions naturally fall in Risk Zones 3 and 4, the Statistical Model is given increased responsibility for increasing Risk Estimations in Zone 1 and limited authority to increase Risk Estimations in Zone 2. Further, in this example embodiment, since the Heuristic .
Model is intended primarily to optimize the detection of fraudulent transactions (and thus to avoid Misses), and since most fraudulent transactions naturally fall in Zones 3 and 4, that model is given full responsibility for producing the basic Risk Estimates in Zone 4 and primary responsibility for producing Risk Estimates in Risk Zone 3. The Statistical Model is then given limited authority to increase Risk Estimates in Zones 2 and 3.
If the risk estimation scores of a collection of models-to-be-fused do not agree, special Limit Surface Logic is applied to minimize either False Alarms or Misses, as the case may be, depending on a merchant-specific Ideal Tradeoff Ratio reflecting each merchant's preference between fraud loss and lost business opportunity.
The Ideal Tradeoff Ratio (ITR) is a statement of a merchant's preference for one risk type (e.g., fraud loss = Type II Error) to another (e.g., lost business opportunity =
Type I Error). For example, a 2:1 ITR implies that, for a particular merchant, two fraud losses cost as much as one lost sale (i.e., that a $2 fraud transaction costs the merchant the same loss as the failure to consummate a good $1 transaction). Ideal Tradeoff Ratio is a function of cost-of goods-sold (COGS) and/or return-on-investment (ROT). If the merchant's COGS is relatively high, and thus the per item ROI is relatively low, the merchant will prefer a lost business opportunity over a fraud loss. In contrast, if the COGS is relatively low, and thus the per item ROI is relatively high, the merchant will have a higher tolerance for a fraud loss than for a lost business opportunity.
Referring now to FIG. 6, a Limit Surface (Type I Limit) is established below the Heuristic Score Surface to help minmize the likelihood of Type I Errors; and a Limit Surface (Type II Limit) is established above the Heuristic Score Surface to help minimize the likelihood of Type II Errors.
If the Heuristic Model Risk Estimate falls in Zone 2 and the Statistical Model Risk Estimate falls between the Type I Limit Surface and the Heuristic Model Surface, the Statistical Model Risk Estimate is allowed to reduce the final Risk Estimate for the apparently non-fraudulent transaction. Otherwise the Heuristic Model produces the final Risk Estimate.
If the Heuristic Model Score falls in Zone 3 and the Statistical Model Score falls between the Type II Limit Surface and the Heuristic Model Surface, the Statistical Model Score is allowed to increase the final Risk Estimate. Otherwise, the Heuristic Model produces the final Risk Estimate.
In general, the contribution of parallel models to the final Risk Estimate is determined during blending by considering the strengths and weaknesses of each model to be blended, in light of the distribution characteristics of the various Risk Zones. The model contributions are adjusted to achieve the Ideal Tradeoff Ratio specified by each merchant.
DYNAMIC SELF-ADJUSTING MULTI-SOURCE ADVERSARIAL RISK
LIKELIHOOD TRACKING MECHANISM
In one approach to evaluating fraud risk, a weighted summation of risk probabilities is transformed by applying a series of mufti-dimensional sigmoidal surface filters with adjustable inflection points to create the optimal balance between maximal risk detection, minimal false positive exposure, and acceptable review levels.
In this approach, five solution components are provided, which are depicted in FIG. 9 and are now described in sequence. Each of the components may be implemented in the form of one or more computer programs, or other software elements (e.g., stored procedures in a database), or in one or more hardware elements, or in a combination of hardware and software elements. Furthermore, the techniques provided herein may be implemented to be progranunatically executed by a computer, whereby one or more _17_ processors execute software code to electronically apply logic embodied in the software code.
A. BALANCED PROBABILISTIC PENALTIES COMPONENT
Fraud risk models attempt to reduce losses from fraudulent transactions, thus, the rules or tests constituent to a model are assigned atomistic weights relative to the respective penalty that each test contributes to the overall probabilistic conclusion derived from the model, or conglomeration of tests. Respective test penalties should reflect the statistical reality, or probability, of fraud given observation of a pattern specified in the respective test.
A Balanced Risk Probabilistic Penalties (Risk Penalties) component of the risk likelihood tracking mechanism addresses the problem of how the individual test result contributions (penalties) to the overall risk estimate are best determined. In one embodiment, it derives individual test outcome penalties from two sets of actuarial data:
the Known Risk Data Sample and the General Data Sample (General Sample).
The Known Risk Data Sample (Risk Sample) consists of a set of transactions of known high risk. The General Sample consists of a much larger randomly sampled set of transactions, known to be mostly risk-free but known also to contain some risky transactions. Due to the randomness of the selection process, the percentage of risky transactions in the General Sample is known to approximate the rate and pattern of occurrence of risky transactions in the universe of all transactions.
The Detection Potential of any individual risk test is approximated by calculating the detection rate of that test in the Risk Sample. Across a range of reasonable estimates for attempted fraud, the Detection Potential of each individual test is used to determine how many fraudulent transactions are expected to be detected by that test in the General Sample. The number of transactions that exceed a decision threshold ("Alarms") is then calculated corresponding to the occurrence of each test in the General Sample across a wide range of decision thresholds. The corresponding ratio of correct risk defections to incorrect referrals ("False Positive Ratio") is calculated.
A risk test penalty, p;, for test i is computed, in one embodiment, according to the formula:
p; = 1.0 / (1.0 + False Positive Ratio of test i) This penalty formula is internal to a risk model and reflects the actuarial conditional probability of risk for each test expressed as a function of the false positive ratio, that is, the likelihood of fraud on any transaction given that the individual test has alarmed. The false positive ratio reflects the number of false alarms incurred from a test for every correct fraud detection from the same test, and is typically used by merchants to adjust their transaction rejection thresholds. This penalty estimate strikes an optimal balance between risk detection power and false positive avoidance at realistic levels of attempted fraud across a wide range of decision threshold values.
B. ADJUSTED WEIGHTED SUMMATION COMPONENT
An Adjusted Weighted Summation component addresses the problem of how the individual test outcome penalties are best combined by computing a Weighted Risk Summation of the activated Probabilistic Penalties according to the general weighted sum algorithm:
E w; c; p;
where 'w;' refers to the weight of test sensor 'i', 'c;' refers to the certainty associated with that test sensor, and 'p;' refers to the probabilistic risk test penalty associated with Risk Test 'i'.
The certainty factors reflect confidence in the reliability of each test.
Thus, the certainty c; for a given test is occasionally updated based upon changes in the confidence in the reliability of the given test. A change in confidence in the reliability of any given test is typically driven by data representing the ongoing real-world transactions. Hence, the confidence in a given test is often related to the reliability and accuracy of the input data, i.e., the available collection of knowledge about real-world credit card transactions, both fraudulent and non-fraudulent.
Furthermore, if the ongoing transaction data indicated that a false positive ratio for a given test has changed, the risk penalty p; is also updated. In one embodiment, the certainty factors and risk penalties periodically update themselves through accessing and processing the collection of transaction data, using algorithms to determine whether updates are necessary. Hence, these parameters are not dynamic, but dynamically self adjusting to ongoing real-world transaction data. The frequency and manner in which the certainty factors and risk penalties are updated are a matter of implementation, and thus, should not be construed as limiting the scope of the invention unless otherwise presented herein.
The weights reflect the 'importance' of each test under modeling assumptions, that is, the importance of a given test in a particular model in view of other tests constituent to the same model. For instance, a model can be represented as a weight vector. Such models could be used to maintain differing patterns of Risk Test importance for different baskets of goods, different merchants, different industry segments and so on.
The use of weight vectors in this way allows for models to be stored and calculated in the most efficient way, and supports dynamic model update. In one embodiment, the weights are subject to merchant specific tuning and can thus be adjusted according to customer preferences. Finally, the Weighted Risk Sum is then adjusted to compensate for the size of the Risk Test Set that actually made non-zero contribution to the Weighted Risk Sum, resulting in an Adjusted Weighted Risk Sum. This adjustment prevents a large Weighted Risk Sum from building up artificially from a large number of very small Test Risk Outcome Penalties.
C. SIGMOIDAL DECISION TRANSFORM COMPONENT
A sigmoidal decision transform component addresses the question of how the resulting combination of test outcome penalties (the Adjusted Weighted Risk Sum) should best be shaped or transformed to optimally serve the needs of the decision domain.
In other words, the decision transform component serves as an optimization tuner for the fraud risk mathematical models relative to the underlying real-world transaction domain, correcting for inherent deficiencies in the respective models. For example, a model based on transaction information from the banking sector is not likely accurate in all areas of the decision domain because the banking sector might not receive formal notification of all possibly fraudulent transactions. For another example, neural network models are limited in effectiveness simply due to the neural modeling process. All models have strengths to be exploited or weaknesses for which to compensate during the fusion process.
Use of sigmoidal transform functions provides the functionality of this component and is applicable to all of the mathematical models, but may be implemented to effect the results of only one or more of the models or of all of the models used in a comprehensive risk evaluation/likelihood estimation scheme. Furthermore, each respective mathematical model can be optimized by a separate respective sigmoidal transform function.
Typically, risk managers want to know how likely it is that a decision will have adverse or favorable consequences. They require a risk estimate that reflects the probability of loss vs. gain. Such estimates are most straightforwardly stated in terms of probabilities. The Sigmoidal Transform computes a number in the range 0-100 to reflect the percent likelihood of risk associated with each model and/or with the fusion result. A
score of zero reflects no risk, zero percent risk likelihood. A score of SO
reflects a 50%
risk likelihood (and conversely a 50% likelihood of non-risk), while a score of 100 reflects a 100% certainty concerning the likelihood of risk.

In the general fusion case, the sigmoidal decision transform component must achieve this mapping by superimposing the classical contour of a sigmoidal function onto the underlying domain pattern of classical detection tradeoff theory. For classical detections of risk, there are four possible outcomes: (1) non-risk was correctly decided;
(2) risk was present but failed to be detected; (3) non-risk was mistakenly classified as risk; and (4) risk was correctly detected.
FIG. 7 is a graph illustrating the foregoing four outcomes. In the example of FIG.
7, a decision threshold value of 57 is assumed, and a fraud attempt rate estimated at 10%
is assumed. The resulting graph 700 has four decision zones comprising a Good Transactions zone 710, Bad Transactions zone 712, Mistaken Sale zone 714, and Mistaken Non-Sale zone 716.
The relationship between the four classes of outcome is characterized by three important decision points (sometimes referred to as inflection points):
(1) The point on the x-axis (the point on the Risk Estimate line) where Failures-To-Detect-Fraud (Mistaken Sales) begin to occur in significant numbers (e.g., point 702), that is, where the slope of the fraudulent transaction distribution becomes mathematically trivial in proximity to zero percentage transactions (i.e., y-axis approaching zero);
(2) The point on the x-axis where the number of Mistaken Rejections become insignificantly small (e.g., point 706), that is, where the slope of the non-fraudulent transaction distribution becomes mathematically trivial in proximity to zero percentage transactions (i.e., y-axis approaclung zero); and (3) The point on the x-axis where Failures-To-Detect-Fraud and Mistaken-Rejections-Of Good-Transactions (Mistaken Non-Sales) are equal (e.g., point 1204), that is, where the fraudulent and non-fraudulent distributions intersect.
A sigmoidal surface is used in mathematics to represent the results of various kinds of transforms. A classical sigmoidal surface also has three important points:
(1) The point on the x-axis where the slope of the transform becomes significant; ' (2) The point on the transform where the significant slope stops increasing and begins to decrease; and (3) The point on the x-axis where the slope of the transform becomes insignificantly small.
In this description, such points of a sigmoidal surface are termed the inflection points of the sigmoidal transform function. According to the approach herein, a classical sigmoidal surface is mapped onto the decision domain by aligning the inflection points of the sigmoidal surface with the decision points of the underlying domain pattern of classical detection tradeoff theory (e.g., the real-world transaction data represented, for example, as fraudulent and non-fraudulent transaction distributions).
FIG. 8 is a graph illustrating a mapping of a sigmoidal transform surface onto the decision domain of FIG. 7 by aligning the inflection points (described above) of a classical sigmoidal surface with the decision points (described above) of the underlying transaction data. A resulting sigmoidal surface 802 has inflection points 804, 806, 808.
The first inflection point 804 is aligned with the x-axis value of the first decision point 702A, as indicated by alignment line 810. A second inflection point 806 is aligned with the x-axis value of the second decision point 704A, as indicated by alignment line 812.
The third decision point 808 is aligned with the x-axis value of the third decision point 706A, as indicated by alignment line 814. The parameters reflecting the mapping of sigmoidal inflection points to underlying transaction decision points are used to define various respective sigmoidal transform functions for respective fraud risk mathematical models, and can be stored in a database for access and dynamic adjustment processes.
In one embodiment, the inflection points are determined by the underlying domain of fraudulent and non-fraudulent transaction distributions. The remaining segments of the sigmoidal surface are determined by the standard formula for the sigmoidal function being used. If the sigmoidal function being used was, for instance, the logistic function, that would determine the resulting surface under the constraints imposed by mapping the inflection points to the decision points.
As a result, the Weighted Risk Sum is transformed into a 100 point percentage risk likelihood estimate. Within the axeas where mistakes of classification are usually made-e.g., Mistaken Sale zone 714 or Mistaken Non-Sale zone 716 of FIG. 7, which produce the highest rates of False Positives and False Negatives-the resulting sigmoidal transform provides maximal discrimination power, resulting in the ability to fine-tune the transform for optimal accuracy. Hence, the models used in the risk likelihood estimation system will provide better performance across all merchants and their respective thresholds, and the transformation of raw scores into transformed scores is more likely to produce an optimum outcome. In one embodiment, additional benefits are provided by allowing dynamic adjustment of the inflection points, thus allowing the decision surface to track changing patterns of risk vs. non-risk based on statistical analysis of the~ongoing, real-time transaction stream.

D. MULTI-SOURCE DIAGNOSTIC FUSION COMPONENT
The Multi-Source Diagnostic Fusion component addresses the question of how more than one such decision domain tailored risk estimate (The Risk Liklihood Estimate) or score should be optimally combined through mufti-source fusion to create the best single point estimate of risk likelihood. In general, in a risk evaluation system there may be two or more risk likelihood recommendations that need to be fused. For example, there may be two or more risk scoring model outputs or recommendations, which may possibly be conflicting. Each model may have different accuracies with respect to a different range of score space or risk space. Traditional heuristic approaches to conflict resolution include simply computing the arithmetic mean or average of the outputs, consensus conflict resolution in which a consensus output is used, and a wiimer-take-all scheme in which the most accurate model for a given score is used. These traditional approaches are inadequate. Therefore, there is a need to blend or fuse the model results in a way that is more accurate than all of the prior methods and to perform a final optimal blending based on merchant's Ideal Tradeoff Ratios.
In one approach, weights are assigned to recommendations that are more accurate for the current range. This is achieved by creating a mufti-dimensional n-space sigmoidal surface corresponding to the two-dimensional surface described above but with one dimension for every score or risk estimate to be fused. Fusion proportions are determined by calculating the point in n-space where the n scores-to-be-fused and the n-dimensional sigmoidal surface (superimposed on the underlying decision domain) intersect.
In the three-dimensional case, Scoring Models A, B, and C are to be combined. The Fusion Proportions of A vs. B, B vs. C, and A vs. C are determined as illustrated in FIG. 1S. In this example it is evident that, from the perspective of Model A, at this Model A score magnitude (approx. S7), the fusion ratio should be 7S:2S in favor of Model A.
These fusion proportions can also be computed for 3-way and, in general, n-way model combinations.
In one embodiment, termed "pair-wise", each pair-proportion is determined from the standpoint of both pair members. For example, the A~B fusion proportion is determined from both the perspective of A (as illustrated) and from the perspective of B.
In the three-Model example, this would yield the following proportional recommendations: AOB'I'A, AOB~I'B, BOC~I'B, BOC~I'C, AOC~I'A, and AOC~I'C, where the notation A~BLl'A refers to the fusion of model scores A and B from the perspective of model score A. These six fusion proportion recommendations would be reduced to a single AOBOC proportion recommendation through the use of any good non-linear classification algorithm such as the radial or elliptical basis-function algorithms. The result might be, in this example, a recommended fusion proportion for A:B:C of 65:25:10, for instance. These proportions could then be used as weights and the fusion accomplished as a weighted average. Alternatively, a non-linear algorithm such as the feed-forward neural network could be trained to make the final optimal blending.
Optimality criteria are stated in the following explanation of n-space surface selection.
The n-dimensional surface that determines these pair-wise fusion proportions is chosen or produced so that the resulting fusion proportions result in the optimal balance between detection power and false positive error across the range of decision thresholds and estimated fraud attempt rates. The simplest way to produce the superset of surfaces from which to choose the optimal one would be through the use of a generate-and-test algorithm, but more powerful and optimal surface prediction algorithms are supported.
Models-to-be-fused can be combined both in series and in parallel. To tlus end, the fusion framework supports the following fusion algebra. Models-to-be-fused can be combined through the use of any n-tuple aggregation fusion algorithm O". Given three models-to-be-fused A, B, and C, and two fusion algorithms O 1 and 02; Models A-B-C
can be fused in parallel as (AO1BO1C) or in series as ((AO1B)02C), ((AUZC)~1B)), or A02(BO1C), allowing for maximal flexibility of fusion function composition.
This approach allows the order of pair-fusions, or more generally the order of n-tuple-fusions, and the fusion techniques themselves to be determined according to a theoretically optimal min-max criterion such as {max(detect(AOBOC)), min(falsePositive(AOBOC))), or any other desirable fusion criteria.
E. POST-FUSION MIN-MAX COMPONENT
A Post-Fusion Min-Max component addresses the question of how to modify that optimal point estimate (The Multi-Source Risk Estimate) so that it does not violate the expectations of experienced system users beyond a reasonable limit. This is achieved through the statistical derivation of an acceptable Minimum Penalty for each domain condition capable of violating such expectations. The Maximum of the Multi-Source Risk Estimate and the Expectation Minimums serves as the final risk estimate.
F. EXAMPLE SYSTEM ARCHITECTURE
FIG. 9 is a block diagram of an example transaction risk assessment system 900 that embodies the foregoing approach.
Transactions to be evaluated, denoted by TXN block 902, enter the system and are subjected to analysis by a number of individual risk tests that are carried out by risk sensors 904. Input to risk sensors 904 may include transactions in a test database 930, such as fraud screening system transactions 932. Risk sensors 904 also are guided by information in a risk database 934 that includes examples of negative transactions, risky transactions, and suspect transactions. Each model in the system includes multiple risk tests, as described above.
Each risk test that alarms on a given transaction contributes a balanced probabilistic risk penalty, which is the conditional risk likelihood associated with that test in the presence of the transaction. As indicated by block 906, a determination of the risk penalty value for a risk test is made, which, in general, is the likelihood of risk balanced against the likelihood of non-risk given that an individual Risk Test alarmed.
Such determination may be computed as (p(Loss~Test), wherein a risk penalty value p is the likelihood of loss given the alarming of a particular test. Penalty values 938 from control database 936 may contribute to the determination at block 906. As described above, in one embodiment, the risk penalty for a given risk test i is determined according to the equation: p; = 1.0 / (1.0 + False Positive Ratio of test i).
The risk penalties that are determined for the multiple tests within a given model are weighted at block 908 (Self Correcting Weighted Summation) using weight values 940 from control database 936, and summed, resulting in creating and storing a summation value. As described above, in one embodiment, an adjusted weighted risk sum of risk penalties for a given model is determined according to the equation: E w; c; p;
The adjusted weighted risk sum is output from a given model and transformed into probabilistic decision space through the use of a sigmoidal transform function, as indicated by block 910 (Sigmoidal Normalization Transform). Values for transform inflection points 942, as described above, are obtained from control database 936. As illustrated in FIG. 9, risk assessment system 900 can have multiple constituent risk models, with different processes and algorithms running as part of each model.
The methods presented above for computation of the risk penalties and the weighted summations are but one of multiple possible implementations. Therefore, the scope of the invention is not limited to any particular fraud risk assessment model, or limited to any particular algorithms or processes within a particular model.
The resulting risk likelihood estimates computed from the fraud risk assessment models are then integrated with any number of other such risk estimates through a process of Multi-Source Diagnostic Fusion, as indicated by block 912. In one embodiment, the fusion process is as described above. Fusion inflection points 944 contribute to multi-source diagnostic fusion in block 912.
The other models computing risk estimates may include, as non-limiting examples, a CyberSource neural network risk model 916, other fraud detection models) 918, and any number of other risk estimation sources 920. Typically, a different sigmoidal normalization transform 910 is derived for each model 915, 916, 91 ~, and 920.
However, the invention is not limited to use of different normalization transforms for the different models.
Furthermore, in one embodiment, a post-fusion transformation 914 is performed on the fused single point risk estimate according to another sigmoidal transform function, to optimize the single point risk estimate even further toward the real-world decision domain. Values for transform inflection points for post-fusion transformation 914 are also typically obtained from control database 936. The post-fusion transform inflection points may, or may not, be equivalent to various transform inflection points 942 used for the sigmoidal normalization transforms 9I0. The resulting mufti-source risk estimate is compared against expectation minimums during a post fusion process 916, whereby the maximum can serve as the final risk estimate for the transaction risk assessment system 900.
In this approach, test penalties are statistically derived from actuarial data to reflect the actual probabilistic risk of loss given that the test alarmed.
This probabilistic risk of loss includes both negative losses (due to fraud, non-payment, etc) and positive losses (due to lost profit opportunities). Thus, the test penalties reflect the actual risk to the merchant in relation to each transaction that alarms a test.
Individual fraud risk assessment models can be maintained as weight vectors.
Thus, models can be maintained to reflect the risks associated with categories of goods sold, geographic delivery locations, merchant groups, or even individual merchants.
Furthermore, weighted summations of risk carry the unwanted side effect that a plurality of small risk likelihood values will add up, creating an artificial appearance of high risk.
The self correcting feature of the weighted summation eliminates this error.
Sigmoidal score transformations (e.g., Sigmoidal Normalization Transform 910), mufti-source diagnostic fusion 912, and post-fusion transformation 914 depend on the creation of a mufti-dimensional surface with adjustable inflection points. The inflection points, and the resulting sigmoidal surfaces are superimposed onto the underlying decision domain through a set of dynamically adjustable "inflection points", allowing the modeler to fit the sigmoidal surface directly onto the domain of interest.
Common sigmoidal transforms do not have the flexibility to f t underlying task domains in this way. In this approach, individual score transformation patterns are maintained as a simple vector of three (x, y) points in raw-score-input by transformed-score-output space.

This allows fine-tuning of the important relationship between review rate, risk detection rate, and false positive ratio.
In the same way, the multi-source fusion process is tailored to the decision domain. Because of the shifting nature of adversarial modeling, it is necessary to constantly adjust the fusion proportions of a multi-source model. The dynamically adjustable inflection points of the mufti-source n-dimensional sigmoidal surface allow its fusion proportions to be dynamically adjusted to remain in optimal register with the problem domain.
FRAUD SCREENING AND SCORING SYSTEM-GENERAL
According to one implementation, the present invention operates in an Internet fraud screening system that examines e-commerce transactions and measures the level of risk associated with each transaction, returning a related risk score back to the merchant in real time. In one aspect, the system uses data validation, highly predictive artificial intelligence pattern matching, network data aggregation and negative file checks to examine numerous factors to calculate fraud risk.
According to one embodiment, the system uses scoring algorithms that are regularly refined through the use of a dynamic closed-loop risk modeling process that enables the service provided by the system to be fine-tuned to adapt to new or changing fraud patterns. Operationally, merchants can request the fraud screening service from the system over the Internet using a secure, open messaging protocol. Upon receipt, the fraud screening system performs several levels of analysis which may include, for example without limitation, utilizing the data elements submitted with the order to perform data .integrity checks and correlation analyses based on the characteristics of the transaction, as well as comparative analysis of the current transaction profile against profiles of known fraudulent transactions and a referenced search of the transaction history database to identify abnormal velocity patterns, name and address changes, and known defrauders. A
risk score is thereby generated and compared to the merchant's specified risk threshold, which may vary depending on the type of transaction or product/service being exchanged.
The result is in turn returned to the merchant for transaction disposition.
FIG. 1 OA is a block diagram showing a general fraud screening system, in which embodiments of the invention may be implemented, including the context in which the fraud screening system may operate.
A merchant 1001 sends a request for service 1003 through one or more networks 1004 to a merchant service provider 1002, and receives a response 1005 that contains a risk score for a particular transaction. Merchant 1001, in FIG. 10A, may comprise one or more software elements that are associated with an online merchant, such as computer programs, Web application programs, CGI or Perl scripts, etc.
Merchant service provider 1002 is an entity that provides electronic commerce services to online merchants. Such services may include, for example, transaction risk management services (including, e.g., fraud screening), payment services, tax computation services, fulfillment management, distribution control, etc.
Merchant service provider 1002 provides such services by or through one or more software elements that communicate through network 1004. For example, the Internet Commerce Suite of CyberSource Corporation (Mountain View, California) may provide such services. The foregoing information about merchant service provider 1002 is provided only to illustrate an example operational context of the invention and does not constitute a required element of the invention.
Network 1004 is one or more local area networks, wide area networks, internetworks, etc. In one embodiment, network 1004 represents the global, packet-switched collection of internetworks known as the Internet. Although one merchant 1001 is shown in FIG. 10A for purposes of illustrating an example, in a practical system, there may be any number of merchants. Request 1003 and response 1005 may be routed over secure channels between merchant 1001 and merchant service provider 1002. In one particular embodiment, each request 1003 and response 1005 is a message that conforms to the Simple Commerce Message Protocol ("SCMP") of CyberSource Corporation.
In one embodiment, one of the services provided by merchant service provider 1002 is risk management services 1006. As part of risk management services 1006, merchant service provider 1002 offers a real-time fraud screening and risk scoring system 1007. The fraud screening and risk scoring system 1007 interacts with a worldwide transaction history database 1008 that contains records of a large plurality of past, completed electronic commerce transactions. In this configuration, fraud screening and risk scoring system 1007 can receive the request for service 1003, consult transaction history database 1008, perform various fraud screening checks, and create and store a risk score for the transaction. When fraud screening is complete, the risk score for the transaction is returned to the merchant in response 1005.
Fraud screening and risk management system 1007 communicates over secure paths 1006A, 1009A with a credit card data source 1009 that has a data modeling and feedback mechanism 1010 and a transaction result database 1011. Credit card data source 1009 is any institution or system that maintains a database of information representing a _28_ large plurality of actual credit card transactions, including both successful, non-fraudulent transactions and transactions that result in charge-backs by an acquiring bank to a card-issuing bank. In one embodiment, credit card data source 1009 is associated with one of the major national credit card associations and therefore includes a large database of credit card transaction and charge-back data.
As discussed fiuther herein, fraud screening and risk scoring system 1007 may use one or more computer-implemented models that include one or more tests and mathematical algorithms to evaluate fraud rzsk associated with a transaction.
The performance of the screening and scoring system may be refined in terms of predictability and accuracy by carrying out data modeling, model output optimization, and feedback based on risk score values generated by the system in comparison to information in transaction result database 1011.
For example, assume that fraud screening and risk scoring system 1007 receives transaction information and assigns a risk score value that indicates a relatively low risk associated with completing the transaction. However, the transaction is in fact fraudulent and results in a charge-back request from the cardholder's card issuer to the merchant 1001. The charge-back request is processed by the credit card data source 1009 and a record of it is made in transaction result database 1011. In this scenario, merchant service provider 1002 can improve the performance of fraud screening and risk scoring system 1007 by periodically exchanging transaction information and risk score values with credit card data source 1009 over path 1006A, and reviewing matching information in transaction result database 1011. Based on characteristics of the matching information, credit card data source 1009 can carry out data modeling and feedback 1010 and provide revised weight values, discrete score values, or even new statistical algorithms over path 1009A to fraud screening and risk scoring system 1007. The'fraud screening and risk scoring system 1007 may then use the new information to carry out subsequent screening evaluations with improved accuracy.
FIG. l OB is a block diagram of a transaction verification system that may be used to implement fraud screening and risk scoring system 1007. Generally, the system~of FIG. l OB can evaluate information representing one or more transactions to result in creating and storing a score value that represents a risk to a merchant associated with processing the transaction. Transaction information 1012, a list of good customers 1014, a list of bad customers 1016 and other pertinent information are received from a merchant who wishes to screen transactions using the system. Transaction information comprises specific information that describes a particular purchase transaction, such as customer name, shipping address, billing address, time, products ordered, price or amount of order, method of payment, card number and expiration date for credit Bard payments, etc. The transaction information 1012 also may include Internet-specific information such as customer domain, email address, IP address, etc.
Transaction history information 1018 also is received from the merchant or maintained by the system. History information 1018 comprises information about past transactions for the same merchant and customer that the system has processed.
Specific values in history information 1018 include the same values described above with respect to transaction information 1012. Thus, history information 1018 may comprise a database of records of past transactions. The history information 1018 is maintained in a database at the service provider that is processing the transactions.
The list of good customers 1014 and list of bad customers 1016 comprise one or more tables or lists of information identifying past customers of the merchant with which the merchant has successfully collected funds for a transaction ("good customers") or experienced non-payment from a disputed transaction, fraud, etc. ("bad customers").
Alternatively, lists 1014 and 1016 may comprise order information that is marked as good or bad by the merchant, and in practice, such Iists are treated as good or bad markings of customers themselves or their Internet identities.
The transaction information 1012 is first subjected to transaction present tests 1010. The transaction present tests 1010 comprise a plurality of computer-implemented filters, tests, computations and other operations that determine whether transaction information 1012 genuinely represents a good transaction. For example, transaction present tests 1010 determine whether transaction information 1012 is expressed in proper form, etc., to arnve at a value representing the relative risk that the customer is attempting to pass a fraudulent order through the system.
If the transaction information 1012 passes transaction present tests 1010, then in comparison operation 1020, transaction information 1012 is compared to history information 1018 to result in creating and storing one or more discrete score values 1030.
Each of the discrete score values 1030 represent a relative risk evaluation carried out individually by transaction present tests 1010 and comparison operation 1020.
The discrete score values 1030 are then applied to a statistical model 1040, resulting in creating and storing at least one or more model score values.
Statistical model 1040 comprises one or more weighted computations or other computer-implemented mathematical operations that apply statistical formulae and weight values to the discrete scores. The purpose of statistical model 1040 is to apply statistical analysis, based on the history information 101 ~ and other records of what transactions have been found in practice to be actually fraudulent, to the discrete score values 1030. The discrete score values 1030 are also applied, in parallel, to a heuristic model 1050 to generate a heuristic model risk estimate.
The resulting model score value from statistical model 1040 and heuristic model risk estimate from heuristic model 1050 are blended using score blending process 1052 to produce an overall final risk estimate. Thus, score blending process 1052 provides a way to combine the heuristic model score with the model score value created as output by statistical model 1040.
Optionally, heuristic model 1050 may also take into account one or more merchant-specific values 1070. Merchant-specific values 1070 may comprise, for example:
1. Product category information, such as a value that limits the maximum number of products in a particular category that a customer is permitted to purchase online in one transaction. Product categories may be specified by the transaction processing system, or specified by the merchant;
2. Selling frequency information, i.e., how often a customer is permitted to buy a particular product over a specified period of time, e.g., a subscription product that can be purchased only once a week;
3. One or more time of day weight values that indicate how important the buyer's time of purchase is, or that indicate what range of time in a day represents a reasonable time at which a buyer is expected to buy a particular product;
4. A "risky host" weight value that reflects an amount of risk associated with a particular host from which a customer order originates, as indicated by the customer's originating IP address or customer's claimed e-mail domain;
5. A gender bias value that indicates whether a specified product is strongly expected to be associated with a purchaser of a particular gender, so that risk increases if the system determines that the purchaser is probably of the other gender;
6. A value indicating the relative weight placed by the merchant on a difference in billing address and shipping address of the customer;
7. A first "velocity" value indicating how often the buyer has made online purchases at all;
8. A second "velocity' value indicating how often the buyer has made online purchases of a specified product category from a specified merchant.
As a result of blending the heuristic model and statistical model scores, a final score value and one or more return code values axe created and stored, as indicated by block 1060. In one embodiment, the final score value is in the range of 0-100, where "0"
represents a transaction that is extremely unlikely to involve fraud and "100"
involves a transaction that is highly likely to represent fraud. The return code values signify special results or other functions.
In one embodiment, one of the return codes comprises one or more bytes of score flags that signal a recommendation to the merchant to reject the transaction regardless of any other criteria of the merchant. For example, score flags may indicate that one of the merchant "velocity" criteria exists in the order, or that prior orders related to the individual who placed the current order are on a fraud list. Alternatively, a score flag may indicate that a customer placing the current order is found in list of bad customers 1016. If prior orders of the customer are on the fraud list, then the current transaction is automatically added to the fraud list as well.
The final score value and return code values are returned to the merchant in one or more messages, using an appropriate protocol. In one particular embodiment, the system of FIG. l OB creates a message that conforms to SCMP, packages the final score value and return code values in the SCMP message, and sends the SCMP message over a secure channel to the merchant.
TRANSACTION PRESENT TESTS
In one embodiment, transaction present tests 1010 comprise a plurality of tests selected from among the following:
1. A "Gibberish city' test detects whether the customer city name value has no vowels, is too short, or has three of the same letter in a row.
2. A "Gibberish last name" test detects whether the customer last name value has no vowels, is too short, or has three of the same letter in a row.
3. A "Gibberish first name" test detects whether the customer first name value received from the merchant has no vowels or has three of the same letter in a row.
4. A "Bad word in email" test detects whether the email address value received from the merchant contains a suspicious string.
5. A "Bad word in first name" test detects whether the first name value received from the merchant contains a string marked as high-risk.
6. A "Bad word in last name" test detects whether the last name value received from the merchant contains a string marked as high-risk.
7. A "Bad word in city" test detects whether the city value received from the merchant contains a string marked as high-risk.
8. A "State changes) found" test detects whether historical orders related to the current request have different state values associated with them.
9. A "High number of credit cards" test detects whether historical orders related to the current request have many different credit card numbers associated with them.
10. A "Long term penalty" test detects whether the customer is attempting to make too many purchases of a product during the long-term hedge period specified by the merchant for the current order.
11. A "Fraud list" test detects whether information identifying the customer is found in an external fraud list.
12. A "Name Changes) Found" test detects whether historical orders related to the current request have different customer last name values associated with them.
13. An "Email/name match" test detects whether the first name value or last name value provided by the customer also appears in the email address value provided by the customer.
14. A "Browser type penalty" test detects whether the customer is using a Web browser program that is marked as high-risk.
15. A "Browser email/email mismatch" test detects whether the email address that is stored as a configuration variable by the customer's Web browser program does not match the email address that the customer provided in the order information.
16. A "No electronic products" test detects whether the order contains no electronic or digital products, as opposed to tangible products.
17. A "Phone number bad length" test detects whether the telephone number value that the customer provided has the wrong number of digits.
18. An "Invalid phone number" test detects whether the telephone number value provided by the customer is invalid. For example, in the United States telephone numbers having the prefix "555" or "111" are invalid.
19. A "Suspicious area code" test detects whether the telephone number value provided by the customer includes a high-risk area code value.
20. An "Area code/state mismatch" test detects whether the area code within the telephone number value is associated with a state other than the state value provided by the customer.
21. An "Area code nonexistent" test detects whether the telephone area code value provided by the customer is not a valid area code or does not exist.
22. A "Toll-free phone number" test detects whether the telephone number value provided by the customer is a toll-free telephone number.
23. A "U.S. address with foreign domain" test detects whether the top-level domain portion of the email address value provided by the customer is associated with a foreign country but the shipping address or billing address value provided by the customer is a U.S. address.
24. A "Bill/ship state mismatch" test detects whether the shipping state value provided for an order does not match the state value in the billing address of the credit card information provided with the order.
25. A "Bill/ship country mismatch" test detects whether the shipping country value provided for an order does not match the country value in the billing address of the credit card information provided with the order.
26. An "AVS" test determines whether a score value associated with the order should be adjusted based on the results of testing the order information using an address verification system.
27. A "B1N penalty" test determines whether a penalty value should apply because the Bank Identification Number ("BIN") received from the customer, which forms the first four to six digits of a conventional credit card number, is marked as high-risk.
28. A "Digits/all lower-case in name" test determines whether the customer name value is all in lower case, or contains numeric digit characters.
29. A "Sequential digits in phone number" test determines whether the customer telephone number value contains multiple consecutive sequential digits.
30. A "Goodguy" test determines whether matching customer information is found in list of good customers 104.
31. An "Unable to verify address" determines whether the customer address is unverifiable; international and military addresses may cause such a result.
32. A "City/state/zip mismatch" test determines whether the city, state, and ZIP code values provided by the customer are not associated with one another based on data available from the Postal Service.
33. An "IP address/hostname mismatch" test determines whether the resolved IP address associated with the customer does not match the hostname portion of the email address provided by the customer.
34. A "No hostname" test determines whether the customer IP address value received as part of the transaction information does not resolve, using the DNS system of the Internet, into a valid hostname value.
35. An "Email in originating domain" test detects whether the email address value provided by the customer is in the same domain as the customer's resolved domain name.
36. An "AOL user from non-AOL host" value detects whether the customer email address value purports that the customer is an America Online user, but the customer is communicating with the merchant from a host other than an AOL host.
37. An "ISP state mismatch" test detects whether a state value that is provided by an Tiiternet Service Provider as part of a resolved domain name does not match the state value provided by the customer. For example, Microsoft Network provides customer state information as part of a resolved domain name, e.g., "chicago-il.us.msn.com," that can be checked against the state value provided by the customer in the transaction information.
3~. A "Netcom oldstyle host" test detects whether the customer is using a shell account of the Internet service provider Netcom that can be used to hide the true identity of the customer.
39. A "Bill country/email mismatch" test detects whether the country value provided by the customer in its billing address information does not match the country value of the customer's email address.
40. A "Bill country/IP host mismatch" test detects whether the country value provided by the customer in its billing address information does not match the country in which the host indicated by the customer's IP address is located, based on resolution using the DNS system.
41. An "Email/IP host country mismatch" test detects whether the country value in the customer's email address does not match the resolved domain name country.

42 A "Whereis check negative" test detects whether the country associated with the customer's IP address, according to the "whereis" database of Network Solutions, Tnc., does not match the country value of the customer's address information.
43. A "Time Risk" test determines the riskiness of the transaction time of day.
44. A "Host Risk" test determines the riskiness of the Internet source location from Which the transaction originates, based on either email address or Internet domain ip address.
45. A "Gender Mismatch Risk" test determines whether the customer gender violates normative expectations in relation to the specified product.
46. Several "Velocity' tests determine the riskiness of the buyer's behavior over time. One of these tests is more general, analyzing the buyer's overall e-commerce activity patterns. The other is more specific, analyzing the buyer's behavior at a specific merchant site with regard to specific categories of goods.
47. A "Gift" test determines whether a mismatch between the billing and shipping addresses is risky or not.
Other tests not specifically identified above may be used.
GIBBERISH TESTS
Transaction present tests 1010 may include one or more tests to determine whether one or more values of transaction information 102 consist of unintelligible or meaningless text ("gibberish"). FIG. 11 is a block diagram of an example embodiment of a gibberish test.
In block 1102, a text value for gibberish testing is received. For example, gibberish testing may be applied to a customer first name value or a last name value received from a merchant for a particular customer.
In block 1104, a table of bi-gram probability values is xeceived. In one embodiment, the table of bi-gram probability values consists of rows representing lettex pairs ("bi-grams") and columns representing the likelihood that a specified bi-gram will appear (a) as the first pair of letters in of a text string, (b) anywhere in the middle of the text string, or (c) as the last pair of letters in a text string, where one column of the table is associated with situation (a), (b), and (c).
An example of a bi-gram is "DA." For this bi-gram, the table could have a value of "80" in the fixst column position, indicating that the letter pair "DA" is likely to appear in the first ordinal position of a true name, as in "DAVID" or "DANIEL." For the same bi-gram, the table could have a value of "20" in the second column position, indicating that a taste name is unlikely to have the letter pair "DA" in the middle of the name. Other numeric values may be used. In one specific embodiment, the table of bi-gram probability values is created and stored manually or automatically based on name information received from a trusted source. For example, name information from U.S. census data may be used.
In block 1106, for each bi-gram in the text value that is received in block 1102, a score value is determined based on the table of bi-gram probability values. In one embodiment, block 1106 involves scanning through each bi-gram in the received text value, and looking up each such bi-gram in the table. For each bi-gram, a score value is generated based on the corresponding probability value that is found in the table. If a bi-gram is not found in the table, a default value may be ascribed, typically representing a low probability.
As indicated in block 1108, the score value determination in block 1106 preferably ignores or screens out received text values that comprise acronyms.
In one embodiment, acronyms are recognized in that a first received text value (e.g., first name) consists of all capital letters and a second received text value (e.g., last name) is mixed case. If an acronym is detected, then the score value determined in block 1106 may be modified or set to a default value.
Special letter combinations may be considered, as indicated in block 1109. For example, in one embodiment, the process of block 1106 attempts to determine an ethnicity associated with the received text values, and if such a determination is made, the values obtained from the table may be adjusted. For example, in a large random sample of names, appearance of the bi-gram "SZ" in the first ordinal position of a last name value may be unlikely. However, that combination is common surnames of Eastern European origin. Accordingly, if the process can determine that a received first name value appears to be a Eastern European name, then certain other letter pairs are more likely to appear in the received text. For example, the letter pair "CZ" may be more likely.
Therefore, in response, the probability value received from the table for such letter pairs may be adj usted.
Separate tables may be created and stored for first name values and last name values. Thus, block 1104, block 1106, block 1108, and block 1109 may involve separate iterations for~a first name value and last name value.

Based on the score values determined in block 1106, the process creates or generates one or more error values or warning values. In one embodiment, block may involve a screening process whereby a score value representing an error is generated only when a bi-gram in the received text value is not found anywhere in the probability table. This option may be used to reduce processing time or when only a rough check of a text value is needed.
As an alternative, in block 1110, a warning value is generated when the received text value comprises a combination of bi-grams that are determined to be unlikely to be associated with a real first name or last name.
As yet another altenzative, as indicated by block 1112, a warning value is generated only when tile received text value comprises a combination of highly unlikely bi-gram values. In this alternative, the warning value is selected to indicate that the received text value is suspicious, but not so unusual as to warrant rejection of a transaction by the merchant.
The table of bi-gram probability values may be updated as additional information becomes available, e.g., at each census interval. Separate tables may be prepared for name values of foreign origin, e.g., Japanese names in kana representation.
GEO-LOCATION TESTS
FIG. 12A is a flow diagram of a process of applying a geo-location test based on area code. The geo-location test of FIG. 12A uses information in two tables.
In block 1202, a city direction table is created and stored. The city direction table has rows that correspond to city values in a customer shipping address. Columns of the table store the city name, a longitude value indicating the absolute longitude of the city, and a latitude value indicating the absolute latitude of the city. In block 1204, an area code direction table is created and stored. The area code direction table has rows that correspond to all possible or known area code values. Columns of the table store one or more longitude values and latitude values that represent the bounds of the area contained within the area code. Alternatively, the area code direction table comprises area code values stored in association with vectors that indicate the boundaries of the area code in terms of latitude and longitude.
Using the values in the tables, information provided by a prospective customer may be tested. In one approach, the city value received from the customer is tested to determine whether it is within,the area code value provided by the customer.
For example, the position of the center of the city indicated in the city value provided by the customer is determined and then correlated to the values in the area code direction table.
Stated another way, the test determines whether the area code specified by the customer actually contains the city specified in the shipping address.
In block 1206, a city value and an area code value are received from the shipping address information in the transaction information for aii order or customer.
As indicated by the dashed lines separating block 1204 and block 1206, the action in block 1206 may occur at a separate time interval from the action of block 1202 and block 1204. The separate time interval may be any duration. Thus block 1202 and block 1204 may be viewed as preparatory steps that may be carried out in an offline mode or at a separate time.
In block 1208, latitude values and longitude values associated with the received city value and the received area code are determined. In one embodiment, a first latitude value and a first longitude value are obtained by looking up the city value in the city direction table, and a second latitude value and a second longitude value are obtained by looking up the received area code value in the area code direction table.
In block 1210, based on the latitude and longitude values, the system tests whether the received city value is within the received area code value. If not, then a penalty value is applied to the transaction, as indicated by block 1212. If the city is properly found within the limits of the specified area code, then no penalty is applied and control continues with other tests or order processing.
FIG. 12B is a flow diagram of a process of applying another geo-location test based on email address. W the test of FIG. 12B, latitude and longitude values are created and stored for each shipping address for all orders from a specified email domain. If a plurality of past orders are concentrated around a particular range of latitude values and longitude values, and a subsequent order is received that provides a shipping address that is outside the range of the latitude values or longitude values, then the subsequent order is reported or tagged as high-risk.
A database table may store the latitude values, longitude values, and information identifying a historical order or a prior customer. In block 1214, a latitude value and a longitude value is created and stored for each shipping address of an order that is processed by a transaction processing system, in association With information identifying a specified email domain. Thus, assume that transaction information is received that includes an email address of the customer in the form "john custname@isp.com,"
and a shipping address for customer John Custname. Based on the city value in the shipping address, the system computes or otherwise determines (e.g., by a lookup in the city direction table that is created as part of FIG. 12A) a latitude value and longitude value for the city value. A record containing the domain value "isp.com," the latitude value, and the longitude value is created and stored in the database. The process of block 1214 is carried out each time a transaction is processed in the system.
In block 1216, an email address of a prospective customer, and a city value from the shipping address portion of transaction information, are received for a new order.
Thus, block 1216 can occur concurrently with block 1214 or at some later time.
In block 1218, a latitude value and a longitude value are determined for the received city value.
In block 1220, the process tests whether the received city value is too far from the domain indicated in the received email address value. Fox example, the process can determine whether the latitude value and longitude value for the received city value, as computed in block 1218, differ too much from a metric that represents corresponding values in the database, e.g., a standard deviation value for the latitude value and longitude value. Alternative mechanisms may be used for determining that the received city value is too far from the geographical area indicated by all other city values for other transactions that reference the same email domain.
If the test of block 1220 is true, then as indicated in block 1222, a penalty is applied to the transaction. Otherwise, control continues with other tests or processing.
This test is effective when a particular Internet Service Provider (ISP) serves a geographically focused customer base. In that case, if an order arrives that includes a shipping address that is far outside the ISP's traditional geographical service area, then the system may hypothesize that the customer is using stolen identity information or stolen credit card information. Such a test may be supplemented with human review of score values in order to ensure that the rate of false negative results ("insults") is not too high.
FIG. 12C is a flow diagram of a geo-location test based upon bank identification number. h1 FIG. 12C, the BIN value of the credit card number provided by a prospective customer is used in geographic consistency screening. In block 1224, the country value of the shipping address in each order processed by the system is stored in association with the BIN value of the credit card number that is specified in the order. Thus, block 1224 involves building a table that associates BIN numbers with the shipping address location of actual orders. Alternatively, in BIN value geo-consistency screening, a range of latitude and longitude values are stored in a database in association with a BIN value.
In block 1226, a country value is received from the shipping address portion of transaction information for a new order. In block 1228, the relative proximity of the current shipping address country value is determined, relative to all other countries associated with the bank identification number that is specified in the order.
Block 1228 may involve, for example, looking up a distance value or weight value in a country distance table that correlates every country of the world with every other country in the world. The distance value or weight value may reflect geographical distance, political distance, cultural distance, etc. For example, a value that correlates the United States to Canada might be very high, whereas a value that correlates the United States to Cuba might be very low because even though the United States is geographically close to Cuba, politically it is distant.
In block 1230, a comparison is made to determine whether the country represented by the country value of the current order is too far from the bank that is associated with the BIN value, as indicated by the country distance table. If so, as indicated in block 1232, a penalty is applied.
Thus, if a plurality of past orders that include a specif ed BIN value are concentrated around a particular range of countries, and a subsequent order is received that provides a shipping address that is outside the range of countries, then the subsequent order is reported or tagged as high-risk. This test is effective when a particular bank serves a geographically focused customer base. In that case, if an order arrives that includes a shipping address that is far outside the bank's traditional geographical service area, then the system may hypothesize that the customer is using stolen identity information or stolen credit card information. For example, assume that a customer presents transaction information 1012 that identifies a credit card number that includes a BIN value associated with a bank headquartered in New York; however, the shipping address for the order includes a country value of "Bulgaria." This may indicate that the order is fraudulent. Such a test may be supplemented with human review of score values in order to ensure that the insult rate is not too high.
HISTORY TESTING-COMPARISON OPERATION
In one embodiment, comparison operation 1020 (FIG. 1 OB) involves comparing transaction information 1012 (FIG. 10B) to history information 1018 (FIG. 1 OB) to result in creating and storing one or more discrete score values 1030 (FIG. l OB).
Such history testing generally involves verifying that the current transaction information 1012 is consistent with all previous transactions associated with an individual.
In one embodiment, transactions are associated with an Internet identity. In this context, an "Internet identity" comprises a unique identifier of a purchaser or other individual who submits order transactions. An Internet identity may comprise an email address. Such an Internet identity value tends to facilitate better screening results in cases where an individual uses a plurality of different email addresses to place orders.
FIG. 13 is a block diagram of alternative embodiments of an Internet identity value. A first embodiment of an Internet identity value 1390A consists of the combination of a hash value based on an email address, as indicated by block 1392, and a hash value based on a credit card BIN value, as indicated by block 1394. Using a value that includes a credit card number as a base element tends to improve accuracy for individuals who use multiple credit cards for different users. In this embodiment, each Internet identity value uniquely identifies a particular email address and card combination.
In any of the foregoing embodiments, in place of a credit card number, the system may use a value that uniquely identifies a purchase method other than a credit card. For example, if a customer uses an electronic check or a stored value card to make a purchase, a check number or card identifier may be used to create the Internet identity value.
Other combinations of values may be used. Referring again to FIG. 13, a second embodiment of an Internet identity value 1390B consists of the combination of a hash value based on an email address, as indicated by block 1392, and a hash value based on a credit card BIN value, as indicated by block 1394, and a hash value based on a shipping address, as indicated by block 1396. This alternative improves accuracy where a plurality of orders use different email addresses and credit card numbers but are all shipped to the same address, especially in the case of residential deliveries.
Still other values could be used. For example, an Internet identity may comprise a first hash value of an prospective purchaser's host IP address, in combination with a second hash value of an email address of a prospective purchaser carried, in combination with a third hash value of a card bank identification number of the prospective purchaser and a fourth hash value based on a shipping address of the prospective purchaser. As another alternative, an Internet identity may comprise a first hash value of a prospective purchaser's hardware device ID value, in combination with a second hash value of either the email address or user ID of the prospective purchaser, in combination with a third hash value of a card bank identification number of the prospective purchaser and with a fourth hash value based on a shipping address of the prospective purchaser.
What is important is to use a value that accurately represents the repeating identity of a particular Internet user across multiple orders, regardless of the host or terminal that the Internet user uses to connect to the network.

Historic transactions in history information 1018 (FIG, l OB) that are associated with the Internet identity of the current transaction may be obtained, for example, by issuing a database query to a database that contains the historical transaction information, and receiving a set of records in response as history information 1018. As records are retrieved, comparison operation 1020 (FIG. 10B) looks for information that signals that the comparison operation should stop. In one embodiment, if any of the records that are returned from the database is for a prior order is on the fraud list, then the system skips comparison operation 1020. This mechanism ensures that unnecessary processing is skipped for orders that are associated with past fraudulent orders, because if such orders are processed using comparison operation 1020, they are certain to end in a negative result. Alternatively, history processing ceases if more than 500 history records are retrieved, and comparison operation 1020 is carried out using only the 500 records that are retrieved. As a result, query time and overall transaction-processing time is reduced.
In addition, Internet identity values that are associated with test identities that are created by merchants to verify system operation are screened out.
In one embodiment, one of the return codes comprises one or more bytes of score flags that signal a recommendation to the merchant to reject the transaction regardless of any other criteria of the merchant. For example, score flags may indicate that one of the merchant "velocity" criteria exists in the order, or that prior orders related to the Internet identity that placed the current order are on a fraud list. Alternatively, a score flag may indicate that a customer placing the current order is found in list of bad customers 1016 (FIG. l OB). If prior orders of the customer are on the fraud list, then the current transaction is automatically added to the fraud list as well.
History information 1018 (FIG. 10 B) may be created and stored by a screening system of the type shown in FIG. 10A as it processes transactions. In one embodiment, the system creates and stores one or more score logs. Each record of a score log identifies a transaction and contains one or more penalty values that resulted from application of the transaction present tests 1010 (FIG. l OB) and other tests of the system to the transaction information 1012 (FIG. l OB). Thus, manual or automated review of the score logs may reveal how a particular transaction was processed in the system.
Further, in one embodiment, the system includes a test scores table, and the system updates values in the test scores table as it processes transactions.
The test scores table contains, for each order, a result value or penalty value for each test that is conducted for an order. In a specific embodiment, the test scores table comprises columns for order number, email address, credit card number, and columns for each test that is carried out as part of transaction present tests 1010 (FIG. l OB). The test scores table may also include the model score value that is provided as output from statistical model 1040 (FIG. l OB), and the f nal score value and return codes that are provided at block 1060 .
(FIG. l OB).
Accordingly, using data in the test scores table, statistical evaluations of the test results may be created. Further, database queries may be applied to the test scores table in order to retrieve orders that are related in some manner. In the past approach, such processing required test parsing of the score logs. In the present approach, such parsing is eliminated, and improved views of the actual significance of tests are provided. As a result, the insult rate of a particular test may be rapidly and regularly evaluated.
Further, if transaction processing results in a high fraud score and the merchant rejects the order in response thereto, triggering a customer inquiry, then the merchant's customer service center can issue a query for the return codes and rapidly determine the exact reason for the high fraud score. The ability to obtain the return codes in a rapid manner also provides the merchant with a weapon against "social engineering,"
a fraud technique in which a declined customer telephones the merchant and attempts fabricates one or more reasons why the order should be accepted, in an attempt to verbally circumvent the merchant's computer-based fraud screens by playing to the emotions of the merchant's customer service representative. Using the disclosed system, the customer service representative can rapidly query the fraud screening system and receive a detailed description of why the order was refused. Such description may be generated based on one or more of the return code values.
HARDWARE OVERVIEW
FIG. 14 is a block diagram that illustrates a computer system 1400 upon which an embodiment of the invention may be implemented. Computer system 1400 includes a bus 1402 or other communication mechanism for communicating information, and a processor 1404 coupled with bus 1402 for processing information. Computer system 1400 also includes a main memory 1406, such as a random access memory (RAM) or other dynamic storage device, coupled to bus 1402 for storing information and instructions to be executed by processor 1404. Main memory 1406 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by processor 1404. Computer system 1400 further includes a read only memory (ROM) 1408 or other static storage device coupled to bus 1402 for storing static information and instructions for processor 1404. A storage device 1410, such as a magnetic disk, optical disk, or magneto-optical disk, is provided and coupled to bus 1402 for storing information and instructions.
Computer system 1400 may be coupled via bus 1402 to a display 1412, such as a cathode ray tube (CRT) or a liquid crystal display (LCD), for displaying information to a computer user. An input device 1414, including alphanumeric and other keys, is coupled to bus 1402 for communicating information and command selections to processor 1404.
Another type of user input device is cursor control 1416, such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections to processor 1404 and for controlling cursor movement on display 1412. This input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allows the device to specify positions in a plane.
The invention is related to the use of computer system 1400 for implementing the techniques described herein. According to one embodiment of the invention, those techniques are performed by computer system 1400 in response to processor 1404 executing one or more sequences of one or more instructions contained in main memory 1406. Such instructions may be read into main memory 1406 from another computer-readable medium, such as storage device 1410. Execution of the sequences of instructions contained in main memory 1406 causes processor 1404 to perform the process steps described herein. In altenlative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions to implement the invention.
Thus, embodiments of the invention are not limited to any specific combination of hardware circuitry and software.
The term "computer-readable medium" as used herein refers to any medium that participates in providing instructions to processor 1404 for execution. Such a medium may take many forms, including but not limited to, non-volatile media, volatile media, and transmission media. Non-volatile media includes, for example, optical, magnetic, or magneto-optical disks, such as storage device 1410. Volatile media includes dynamic memory, such as main memory 1406. Transmission media includes coaxial cables, copper wire and fiber optics, including the wires that comprise bus 1402.
Transmission media can also take the form of acoustic or light waves, such as those generated during radio-wave and infra-red data communications.
Common forms of computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, or any other magnetic medium, a CD-ROM, any other optical medium, punchcards, papertape, any other physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, any other memory chip or cartridge, a carrier wave as described hereinafter, or any other medium from which a computer can read.
Various forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to processor 1404 for execution.
For example, the instructions may initially be carried on a magnetic disk of a remote computer. The remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to computer system 1400 can receive the data on the telephone line and use an infra-red transmitter to convert the data to an infra-red signal. An infra-red detector can receive the data carried in the infra-red signal and appropriate circuitry can place the data on bus 1402. Bus 1402 carries the data to main memory 1406, from which processor 1404 retrieves and executes the instructions. The instructions received by main memory 1406 may optionally be stored on storage device 1410 either before or after execution by processor 1404.
Computer system 1400 also includes a communication interface 1418 coupled to bus 1402. Communication interface 1418 provides a two-way data communication coupling to a network link 1420 that is connected to a local network 1422. For example, communication interface 1418 may be an integrated services digital network (ISDN) card or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, communication interface 1418 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN.
Wireless links may also be implemented. In any such implementation, communication interface 1418 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.
Network link 1420 typically provides data communication through one or more networks to other data devices. For example, network link 1420 may provide a connection through local network 1422 to a host computer 1424 or to data equipment operated by an Internet Service Provider (ISP) 1426. ISP 1426 in turn provides data communication services through the world wide packet data communication network now commonly referred to as the "Internet" 1428. Local network 1422 and Internet 1428 both use electrical, electromagnetic or optical signals that carry digital data streams. The signals through the various networks and the signals on network link 1420 and through communication interface 1418, which carry the digital data to and from computer system 1400, are exemplary forms of carrier waves transporting the information.
Computer system 1400 can send messages and receive data, including program code, through the network(s), network link 1420 and communication interface 1418. In the Internet example, a server 1430 might transmit a requested code for an application program through Internet 1428, ISP 1426, local network 1422 and communication interface 1418.
The received code may be executed by processor 1404 as it is received, and/or stored in storage device 1410, or other non-volatile storage for later execution. In this manner, computer system 1400 may obtain application code in the form of a carrier wave.
EXTENSIONS AND ALTERNATIVES
Alternative embodiments of the invention are described throughout the foregoing description, and in locations that best facilitate understanding the context of the embodiments. Furthermore, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention.
Therefore, the specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
In addition, in this description certain process steps are set forth in a particular order, and alphabetic and alphanumeric labels may be used to identify certain steps.
Unless specifically stated in the description, embodiments of the invention are not necessarily limited to any particular order of carrying out such steps. In particular, the labels are used merely for convenient identification of steps, and are not intended to specify or require a particular order of carrying out such steps.

Claims (36)

What is claimed is:
1. A method for evaluating fraud risk in an electronic commerce transaction and providing a representation of the fraud risk to a merchant using electronic communication, the method comprising the computer-implemented steps of:
receiving transaction information;
applying the transaction information to one or more fraud risk mathematical models wherein each mathematical model produces a respective raw score; and transforming the one or more respective raw scores with respective sigmoidal functions to generate respective risk estimates.
2. The method claim 1, wherein two or more fraud risk mathematical models are applied to the transaction information to generate respective risk estimates, the method comprising the steps of:
combining two or more of the respective risk estimates, using fusion proportions that are associated with the two or more fraud risk mathematical models that generate the respective risk estimates, to produce a single point risk estimate for the transaction; and transforming the single point risk estimate with a sigmoidal function to produce an optimized single point risk estimate for the transaction.
3. The method of claim 2 wherein each of the two or more respective risk estimates is based on a respective statistical mathematical model from a set of one or more statistical mathematical models or on a respective heuristic mathematical model from a set of one or more heuristic mathematical models, and wherein at least one respective risk estimate is based on a respective statistical mathematical model and at least one other respective risk estimate is based on a respective heuristic mathematical model, and wherein the step of combining two or more of the respective risk estimates comprises the steps of:

establishing either the respective statistical mathematical model or the respective heuristic mathematical model as a first scoring authority for establishing the boundaries of fraud risk zones from a set of fraud risk zones;
establishing the first scoring authority with authority to modify at least one respective risk estimate, from the two or more respective risk estimates, that is in a first particular fraud risk zone from the set of fraud risk zones, based on an intent of the first scoring authority with respect to transaction information;
establishing as a second scoring authority the other of the respective statistical and heuristic mathematical models that is not the first scoring authority; and establishing the second scoring authority with authority to modify at least one respective risk estimate, from the two or more respective risk estimates, that is in a second particular fraud risk zone from the set of fraud risk zones that is different than the first particular fraud risk zone, based on an intent of the second scoring authority with respect to transaction information.
4. The method of claim 2 wherein the step of combining two or more of the respective risk estimates comprises the steps of:
analyzing performance characteristics of the two or more fraud risk mathematical models in view of distribution characteristics of a set of fraud risk zones, wherein the distribution characteristics are in terms of a relationship between fraudulent and non-fraudulent transactions and a percentage of transactions associated with a risk estimate; and determining a respective contribution from each of the two or more fraud risk mathematical models to the single point risk estimate for the transaction, based on the analyzed performance characteristics of the two or more fraud risk mathematical models.
5. The method of claim 4 comprising the step of:
adjusting the respective contributions from the two or more fraud risk mathematical models based on a merchant preference for one fraud risk type in relation to another fraud risk type.
6. The method of claim 2 comprising the steps of:
determining intermediate fusion proportions that are associated with the respective risk estimates from a perspective of each of the two or more fraud risk mathematical models; and reducing the intermediate fusion proportions to the fusion proportions that are associated with the two or more fraud risk mathematical models that generate the respective risk estimates, based on a non-linear classification algorithm.
7. The method of claim 1 wherein the one or more fraud risk mathematical models each include a plurality of risk tests, the method comprising:
computing a respective risk test penalty for at least some of the plurality of risk tests of the one or more fraud risk mathematical models, wherein the respective risk test penalty is equal to the inverse of the sum of one and a false positive ratio for a respective risk test and wherein the false positive ratio is a ratio of correct risk detections to incorrect referrals generated by the respective risk test;
and computing a weighted summation of the risk test penalties to produce the respective raw score for the transaction.
8. The method of claim 1 comprising:
deriving the respective sigmoidal functions to approximate a relationship between risk estimates produced by one or more fraud risk detection models and a percentage of transactions associated with a risk estimate, in terms of distributions of fraudulent and non-fraudulent transactions; and wherein the step of transforming is based on the respective sigmoidal functions.
9. The method of claim 8 wherein the relationship is defined by:
a first point at which the slope of the fraudulent transaction distribution becomes mathematically trivial in proximity to a zero percentage of transactions;
a second point at which the slope of the non-fraudulent transaction distribution becomes mathematically trivial in proximity to a zero percentage of transactions;
and a third point at which the fraudulent and non-fraudulent transaction distributions intersect.
10. The method of claim 9 wherein the step of deriving the respective sigmoidal functions is performed by constraining the respective sigmoidal functions to the abscissas of the first, second, and third points.
11. The method of claim 8 wherein the step of deriving the respective sigmoidal functions comprises the step of deriving respective sigmoidal functions that are dynamically adjustable based on a change to the relationship.
12. A method for assessing the likelihood of fraud given a fraud detection response from a fraud risk test in a fraud risk detection mathematical model, the method comprising the step of:
computing a fraud risk test penalty equal to the inverse of the sum of one and a false positive ratio for the fraud risk test, wherein the false positive ratio is a ratio of correct risk detections to incorrect referrals generated by the fraud risk test.
13. A method for programmatically evaluating fraud risk in an electronic commerce transaction and providing a representation of the fraud risk to a merchant via a network, the method comprising:
receiving purchasing information at a server via the network, wherein at least some of the purchasing information is provided by a prospective purchaser of goods or services or goods and services from the merchant;
computing a respective raw score from one or more fraud risk mathematical models, wherein each respective raw score is based at least in part on the purchasing information;
accessing first transformation information from a database to generate one or more first sigmoidal functions that are based at least in part on historical transaction information;
computing a respective risk estimate by transforming a raw score with a respective sigmoidal function;
if there are multiple risk estimates, combining respective risk estimates using fusion proportions to produce a single point risk estimate for the electronic transaction;
accessing second transformation information from a database to generate a second sigmoidal function;
computing an optimized single point risk estimate for the transaction by transforming the single point risk estimate with the second sigmoidal function;
and transmitting a representation of the optimized single point risk estimate to the merchant via the network.
14. A computer-readable medium carrying one or more sequences of instructions for evaluating fraud risk in an electronic commerce transaction and providing a representation of the fraud risk to a merchant using electronic communication, which instructions, when executed by one or more processors, cause the one or more processors to carry out the steps of:
receiving transaction information;
applying the transaction information to one or more fraud risk mathematical models wherein each mathematical model produces a respective raw score; and transforming the one or more respective raw scores with respective sigmoidal functions to generate respective risk estimates.
15. The computer-readable medium of claim 14 wherein two or more fraud risk mathematical models are applied to the transaction information to generate respective risk estimates, further comprising instructions which, when executed by the one or more processors, cause the one or more processors to carry out the steps of:
combining two or more of the respective risk estimates, using fusion proportions that are associated with the respective risk estimates, to produce a single point risk estimate for the transaction; and transforming the single point risk estimate with a sigmoidal function to produce an optimized single point risk estimate for the transaction.
16. The computer-readable medium of claim 15 wherein each of the two or more respective risk estimates is based on a respective statistical mathematical model from a set of one or more statistical mathematical models or on a respective heuristic mathematical model from a set of one or more heuristic mathematical models, and wherein at least one respective risk estimate is based on a respective statistical mathematical model and at least one other respective risk estimate is based on a respective heuristic mathematical model, and wherein the instructions for combining two or more of the respective risk estimates comprises instructions which, when executed by the one or more processors, cause the one or more processors to carry out the steps of:
establishing either the respective statistical mathematical model or the respective heuristic mathematical model as a first scoring authority for establishing the boundaries of fraud risk zones from a set of fraud risk zones;
establishing the first scoring authority with authority to modify at least one respective risk estimate, from the two or more respective risk estimates, that is in a first particular fraud risk zone from the set of fraud risk zones, based on an intent of the first scoring authority with respect to transaction information;
establishing as a second scoring authority the other of the respective statistical and heuristic mathematical models that is not the first scoring authority; and establishing the second scoring authority with authority to modify at least one respective risk estimate, from the two or more respective risk estimates, that is in a second particular fraud risk zone from the set of fraud risk zones that is different than the first particular fraud risk zone, based on an intent of the second scoring authority with respect to transaction information.
17. The computer-readable medium of claim 15 wherein the instructions for combining two or more of the respective risk estimates comprises instructions which, when executed by the one or more processors, cause the one or more processors to carry out the steps of:
analyzing performance characteristics of the two or more fraud risk mathematical models in view of distribution characteristics of a set of fraud risk zones, wherein the distribution characteristics are in terms of a relationship between fraudulent and non-fraudulent transactions and a percentage of transactions associated with a risk estimate; and determining a respective contribution from each of the two or more fraud risk mathematical models to the single point risk estimate for the transaction, based on the analyzed performance characteristics of the two or more fraud risk mathematical models.
18. The computer-readable medium of claim 17, further comprising instructions which, when executed by the one or more processors, cause the one or more processors to carry out the steps of:
adjusting the respective contributions from the two or more fraud risk mathematical models based on a merchant preference for one fraud risk type in relation to another fraud risk type.
19. The computer-readable medium of claim 1S further comprising instructions which, when executed by the one or more processors, cause the one or more processors to carry out the steps of:
determining intermediate fusion proportions that are associated with the respective risk estimates from a perspective of each of the two or more fraud risk mathematical models; and reducing the intermediate fusion proportions to the fusion proportions that are associated with the two or more fraud risk mathematical models that generate the respective risk estimates, based on a non-linear classification algorithm.
20. The computer-readable medium of claim 14 wherein the one or more fraud risk mathematical models each include a plurality of risk tests, further comprising instructions which, when executed by the one or more processors, cause the one or more processors to carry out the steps of:
computing a respective risk test penalty for at least some of the plurality of risk tests of the one or more fraud risk mathematical models, wherein the respective risk test penalty is equal to the inverse of the sum of one and a false positive ratio for a respective risk test and wherein the false positive ratio is a ratio of correct risk detections to incorrect referrals generated by the respective risk test;
and computing a weighted summation of the risk test penalties to produce the respective raw score for the transaction.
21. The computer-readable medium of Claim 14, further comprising instructions which, when executed by the one or more processors, cause the one or more processors to carry out the steps of:
deriving the respective sigmoidal functions to approximate a relationship between risk estimates produced by one or more fraud risk detection models and a percentage of transactions associated with a risk estimate, in terms of distributions of fraudulent and non-fraudulent transactions; and wherein the step of transforming is based on the respective sigmoidal functions.
22. The computer-readable of claim 21 wherein the relationship is defined by:
a first point at which the slope of the fraudulent transaction distribution becomes mathematically trivial in proximity to a zero percentage of transactions;
a second point at which the slope of the non-fraudulent transaction distribution becomes mathematically trivial in proximity to a zero percentage of transactions;
and a third point at which the fraudulent and non-fraudulent transaction distributions intersect.
23. The computer-readable medium of claim 22 wherein the instructions for deriving the respective sigmoidal functions comprises instructions for constraining the respective sigmoidal functions to the abscissas of the first, second, and third points.
24. The computer-readable medium of claim 21 wherein the instructions for deriving the respective sigmoidal functions comprises instructions for deriving respective sigmoidal functions that are dynamically adjustable based on a change to the relationship.
25. A computer-readable medium carrying one or more sequences of instructions for assessing the likelihood of fraud given a fraud detection response from a fraud risk test in a fraud risk detection mathematical model, which instructions, when executed by one or more processors, cause the one or more processors to carry out the steps of computing a fraud risk test penalty equal to the inverse of the sum of one and a false positive ratio for the fraud risk test, wherein the false positive ratio is a ratio of correct risk detections to incorrect referrals generated by the fraud risk test.
26. An apparatus for evaluating fraud risk in an electronic commerce transaction and providing a representation of the fraud risk to a merchant using electronic communication, comprising:
means for receiving transaction information;
means for applying the transaction information to one or more fraud risk mathematical models wherein each mathematical model produces a respective raw score; and means for transforming the one or more respective raw scores with respective sigmoidal functions to generate respective risk estimates.
27. An apparatus for evaluating fraud risk in an electronic commerce transaction and providing a representation of the fraud risk to a merchant using electronic communication, comprising:
a network interface that is coupled to the data network for receiving one or more packet flows therefrom;
a processor;
one or more stored sequences of instructions which, when executed by the processor, cause the processor to carry out the steps of:
receiving transaction information;

applying the transaction information to one or more fraud risk mathematical models wherein each mathematical model produces a respective raw score; and transforming the one or more respective raw scores with respective sigmoidal functions to generate respective risk estimates.
28. The apparatus of claim 27 wherein two or more fraud risk mathematical models axe applied to the transaction information to generate respective risk estimates, wherein the one or more stored sequences of instructions, when executed by the processor, cause the processor to carry out the steps of:
combining two or more of the respective risk estimates, using fusion proportions that are associated with the two or more fraud risk mathematical models that generate the respective risk estimates, to produce a single point risk estimate for the transaction; and transforming the single point risk estimate with a sigmoidal function to produce an optimized single point risk estimate for the transaction.
29. The apparatus of claim 28 wherein each of the two or more respective risk estimates is based on a respective statistical mathematical model from a set of one or more statistical mathematical models or on a respective heuristic mathematical model from a set of one or more heuristic mathematical models, and wherein at least one respective risk estimate is based on a respective statistical mathematical model and at least one other respective risk estimate is based on a respective heuristic mathematical model, and wherein the instructions for carrying out the step of combining two or more of the respective risk estimates comprises instructions, when executed by the processor, that cause the processor to carry out the steps of:
establishing either the respective statistical mathematical model or the respective heuristic mathematical model as a first scoring authority for establishing the boundaries of fraud risk zones from a set of fraud risk zones;
establishing the first scoring authority with authority to modify at least one respective risk estimate, from the two or more respective risk estimates, that is in a first particular fraud risk zone from the set of fraud risk zones, based on an intent of the first scoring authority with respect to transaction information;
establishing as a second scoring authority the other of the respective statistical and heuristic mathematical models that is not the first scoring authority; and establishing the second scoring authority with authority to modify at least one respective risk estimate, from the two or mode respective risk estimates, that is in a second particular fraud risk zone from the set of fraud risk zones that is different than the first particular fraud risk zone, based on an intent of the second scoring authority with respect to transaction information.
30. The apparatus of claim 29 wherein the instructions for carrying out the step of combining two or more of the respective risk estimates comprises instructions, when executed by the processor, that cause the processor to carry out the steps of:
analyzing performance characteristics of the two or more fraud risk mathematical models in view of distribution characteristics of a set of fraud risk zones, wherein the distribution characteristics are in terms of a relationship between fraudulent and non-fraudulent transactions and a percentage of transactions associated with a risk estimate; and determining a respective contribution from each of the two or more fraud risk mathematical models to the single point risk estimate for the transaction, based on the analyzed performance characteristics of the two or more fraud risk mathematical models.
31. The apparatus of claim 29 wherein the one or more stored sequences of instructions, when executed by the processor, cause the processor to carry out the steps of:
adjusting the respective contributions from the two or more fraud risk mathematical models based on a merchant preference for one fraud risk type in relation to another fraud risk type.
32. The apparatus of claim 28 wherein the one or more stored sequences of instructions, when executed by the processor, cause the processor to carry out the steps of:
determining intermediate fusion proportions that are associated with the respective risk estimates from a perspective of each of the two or more fraud risk mathematical models; and reducing the intermediate fusion proportions to the fusion proportions that are associated with the two or more fraud risk mathematical models that generate the respective risk estimates, based on a non-linear classification algorithm.
33. The apparatus of claim 27 wherein the one or more fraud risk mathematical models each include a plurality of risk tests, and wherein the one or more stored sequences of instructions, when executed by the processor, cause the processor to carry out the steps of:
computing a respective risk test penalty for at least some of the plurality of risk tests of the one or more fraud risk mathematical models, wherein the respective risk test penalty is equal to the inverse of the sum of one and a false positive ratio for a respective risk test and wherein the false positive ratio is a ratio of correct risk detections to incorrect referrals generated by the respective risk test;
and computing a weighted summation of the risk test penalties to produce the respective raw score for the transaction.
34. The apparatus of claim 27 wherein the one or more stored sequences of instructions, when executed by the processor, cause the processor to carry out the steps of:
deriving the respective sigmoidal functions to approximate a relationship between risk estimates produced by one or more fraud risk detection models and a percentage of transactions associated with a risk estimate, in terms of distributions of fraudulent and non-fraudulent transactions; and wherein the step of transforming is based on the respective sigmoidal functions.
35. The apparatus of claim 34 wherein the relationship is defined by:
a first point at which the slope of the fraudulent transaction distribution becomes mathematically trivial in proximity to a zero percentage of transactions;
a second point at which the slope of the non-fraudulent transaction distribution becomes mathematically trivial in proximity to a zero percentage of transactions;
and a third point at which the fraudulent and non-fraudulent transaction distributions intersect.
36. The apparatus of claim 35 wherein the instructions for deriving the respective sigmoidal functions comprises instructions, when executed by the processor, cause the processor to carry out the step of constraining the respective sigmoidal functions to the abscissas of the first, second, and third points.
CA002447512A 2001-05-30 2002-05-16 Method and apparatus for evaluating fraud risk in an electronic commerce transaction Abandoned CA2447512A1 (en)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US29485201P 2001-05-30 2001-05-30
US60/294,852 2001-05-30
US10/142,271 2002-05-08
US10/142,271 US7865427B2 (en) 2001-05-30 2002-05-08 Method and apparatus for evaluating fraud risk in an electronic commerce transaction
PCT/US2002/015670 WO2002097563A2 (en) 2001-05-30 2002-05-16 Method and apparatus for evaluating fraud risk in an electronic commerce transaction

Publications (1)

Publication Number Publication Date
CA2447512A1 true CA2447512A1 (en) 2002-12-05

Family

ID=26839930

Family Applications (1)

Application Number Title Priority Date Filing Date
CA002447512A Abandoned CA2447512A1 (en) 2001-05-30 2002-05-16 Method and apparatus for evaluating fraud risk in an electronic commerce transaction

Country Status (6)

Country Link
US (3) US7865427B2 (en)
EP (1) EP1390833A4 (en)
JP (1) JP2004537781A (en)
AU (1) AU2002311941A1 (en)
CA (1) CA2447512A1 (en)
WO (1) WO2002097563A2 (en)

Families Citing this family (466)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7403922B1 (en) * 1997-07-28 2008-07-22 Cybersource Corporation Method and apparatus for evaluating fraud risk in an electronic commerce transaction
AU763571B2 (en) 1998-12-23 2003-07-24 Chase Manhattan Bank, The System and method for integrating trading operations including the generation, processing and tracking of and trade documents
US8793160B2 (en) 1999-12-07 2014-07-29 Steve Sorem System and method for processing transactions
US7831467B1 (en) 2000-10-17 2010-11-09 Jpmorgan Chase Bank, N.A. Method and system for retaining customer loyalty
US7809650B2 (en) * 2003-07-01 2010-10-05 Visa U.S.A. Inc. Method and system for providing risk information in connection with transaction processing
US8849716B1 (en) 2001-04-20 2014-09-30 Jpmorgan Chase Bank, N.A. System and method for preventing identity theft or misuse by restricting access
US8433627B2 (en) * 2001-06-07 2013-04-30 Fairshare, Llc Rapid tax collection system and method
WO2002099598A2 (en) 2001-06-07 2002-12-12 First Usa Bank, N.A. System and method for rapid updating of credit information
US7266839B2 (en) 2001-07-12 2007-09-04 J P Morgan Chase Bank System and method for providing discriminated content to network users
US7835919B1 (en) 2001-08-10 2010-11-16 Freddie Mac Systems and methods for home value scoring
US7711574B1 (en) 2001-08-10 2010-05-04 Federal Home Loan Mortgage Corporation (Freddie Mac) System and method for providing automated value estimates of properties as of a specified previous time period
US8020754B2 (en) 2001-08-13 2011-09-20 Jpmorgan Chase Bank, N.A. System and method for funding a collective account by use of an electronic tag
US7987501B2 (en) 2001-12-04 2011-07-26 Jpmorgan Chase Bank, N.A. System and method for single session sign-on
US7657482B1 (en) * 2002-07-15 2010-02-02 Paymentech, L.P. System and apparatus for transaction fraud processing
US7451095B1 (en) * 2002-10-30 2008-11-11 Freddie Mac Systems and methods for income scoring
US7797166B1 (en) 2002-10-30 2010-09-14 Federal Home Loan Mortgage Corporation (Freddie Mac) Systems and methods for generating a model for income scoring
US7870078B2 (en) * 2002-11-01 2011-01-11 Id Insight Incorporated System, method and computer program product for assessing risk of identity theft
US8301493B2 (en) 2002-11-05 2012-10-30 Jpmorgan Chase Bank, N.A. System and method for providing incentives to consumers to share information
US7249143B1 (en) * 2002-12-10 2007-07-24 Capital One Financial Corporation System and method for managing fulfillment data associated with a fulfillment system
US7346551B2 (en) 2002-12-23 2008-03-18 Cybersource Corporation Method and apparatus for custom strategy specification in a hosted electronic transaction service system
US7143095B2 (en) * 2002-12-31 2006-11-28 American Express Travel Related Services Company, Inc. Method and system for implementing and managing an enterprise identity management for distributed security
US20110202565A1 (en) * 2002-12-31 2011-08-18 American Express Travel Related Services Company, Inc. Method and system for implementing and managing an enterprise identity management for distributed security in a computer system
US20040199462A1 (en) * 2003-04-02 2004-10-07 Ed Starrs Fraud control method and system for network transactions
JP2004348536A (en) * 2003-05-23 2004-12-09 Intelligent Wave Inc History information addition program, fraudulent determination program using history information, and fraudulent determination system using history information
US8306907B2 (en) 2003-05-30 2012-11-06 Jpmorgan Chase Bank N.A. System and method for offering risk-based interest rates in a credit instrument
US9412123B2 (en) 2003-07-01 2016-08-09 The 41St Parameter, Inc. Keystroke analysis
US20050055373A1 (en) * 2003-09-04 2005-03-10 Forman George H. Determining point-of-compromise
US8175908B1 (en) 2003-09-04 2012-05-08 Jpmorgan Chase Bank, N.A. Systems and methods for constructing and utilizing a merchant database derived from customer purchase transactions data
KR100648064B1 (en) * 2004-01-14 2006-11-23 주식회사 케이티프리텔 mobile terminal for certification, E-commerce system and method using the terminal
US10999298B2 (en) 2004-03-02 2021-05-04 The 41St Parameter, Inc. Method and system for identifying users and detecting fraud by use of the internet
US8762283B2 (en) * 2004-05-03 2014-06-24 Visa International Service Association Multiple party benefit from an online authentication service
US7497374B2 (en) * 2004-09-17 2009-03-03 Digital Envoy, Inc. Fraud risk advisor
US7543740B2 (en) * 2004-09-17 2009-06-09 Digital Envoy, Inc. Fraud analyst smart cookie
US20060064374A1 (en) * 2004-09-17 2006-03-23 David Helsper Fraud risk advisor
US7797199B2 (en) * 2004-10-15 2010-09-14 Rearden Commerce, Inc. Fraudulent address database
US10134202B2 (en) * 2004-11-17 2018-11-20 Paypal, Inc. Automatic address validation
US20060111927A1 (en) 2004-11-19 2006-05-25 International Business Machines Corporation System, method and program for estimating risk of disaster in infrastructure
US8740069B2 (en) * 2005-01-26 2014-06-03 Heng Kah Choy Fraud-free payment for internet purchases
CA2602720A1 (en) * 2005-03-24 2006-09-28 Accenture Global Services Gmbh Risk based data assessment
US20060224499A1 (en) * 2005-03-29 2006-10-05 First American Real Estate Solutions, L.P. Method and apparatus for computing a loan quality score
US7519562B1 (en) * 2005-03-31 2009-04-14 Amazon Technologies, Inc. Automatic identification of unreliable user ratings
US7877326B2 (en) * 2005-04-16 2011-01-25 At&T Intellectual Property I, L.P. Methods, systems, and products for collaborative authorizations in electronic commerce
US7630924B1 (en) * 2005-04-20 2009-12-08 Authorize.Net Llc Transaction velocity counting for fraud detection
US9571652B1 (en) * 2005-04-21 2017-02-14 Verint Americas Inc. Enhanced diarization systems, media and methods of use
US8639757B1 (en) 2011-08-12 2014-01-28 Sprint Communications Company L.P. User localization using friend location information
US7401731B1 (en) 2005-05-27 2008-07-22 Jpmorgan Chase Bank, Na Method and system for implementing a card product with multiple customized relationships
EP1732034A1 (en) * 2005-06-06 2006-12-13 First Data Corporation System and method for authorizing electronic payment transactions
US7665658B2 (en) * 2005-06-07 2010-02-23 First Data Corporation Dynamic aggregation of payment transactions
US20060287947A1 (en) * 2005-06-16 2006-12-21 Toms Alvin D Non-payment risk assessment
US7925578B1 (en) 2005-08-26 2011-04-12 Jpmorgan Chase Bank, N.A. Systems and methods for performing scoring optimization
US7668769B2 (en) * 2005-10-04 2010-02-23 Basepoint Analytics, LLC System and method of detecting fraud
US8874477B2 (en) 2005-10-04 2014-10-28 Steven Mark Hoffberg Multifactorial optimization system and method
US7818238B1 (en) * 2005-10-11 2010-10-19 Jpmorgan Chase Bank, N.A. Upside forward with early funding provision
CA2625907A1 (en) * 2005-10-12 2007-04-19 First Data Corporation System and method for authorizing electronic payment transactions
US8346638B2 (en) * 2005-10-26 2013-01-01 Capital One Financial Corporation Systems and methods for processing transaction data to perform a merchant chargeback
US7860783B2 (en) * 2005-11-07 2010-12-28 Fair Isaac Corporation Account-level fraud detector and associated methods
US8938671B2 (en) 2005-12-16 2015-01-20 The 41St Parameter, Inc. Methods and apparatus for securely displaying digital images
US11301585B2 (en) 2005-12-16 2022-04-12 The 41St Parameter, Inc. Methods and apparatus for securely displaying digital images
US20070150949A1 (en) * 2005-12-28 2007-06-28 At&T Corp. Anomaly detection methods for a computer network
US7808916B1 (en) * 2005-12-28 2010-10-05 At&T Intellectual Property Ii, L.P. Anomaly detection systems for a computer network
US8280805B1 (en) 2006-01-10 2012-10-02 Sas Institute Inc. Computer-implemented risk evaluation systems and methods
EP1816595A1 (en) * 2006-02-06 2007-08-08 MediaKey Ltd. A method and a system for identifying potentially fraudulent customers in relation to network based commerce activities, in particular involving payment, and a computer program for performing said method
US7533798B2 (en) * 2006-02-23 2009-05-19 Rockwell Automation Technologies, Inc. Data acquisition and processing system for risk assessment
US7912773B1 (en) 2006-03-24 2011-03-22 Sas Institute Inc. Computer-implemented data storage systems and methods for use with predictive model systems
US7966256B2 (en) * 2006-09-22 2011-06-21 Corelogic Information Solutions, Inc. Methods and systems of predicting mortgage payment risk
US7587348B2 (en) * 2006-03-24 2009-09-08 Basepoint Analytics Llc System and method of detecting mortgage related fraud
US8151327B2 (en) 2006-03-31 2012-04-03 The 41St Parameter, Inc. Systems and methods for detection of session tampering and fraud prevention
US8099329B2 (en) 2006-04-25 2012-01-17 Uc Group Limited Systems and methods for determining taxes owed for financial transactions conducted over a network
BRPI0710981A2 (en) * 2006-04-25 2012-02-28 Uc Group Ltd systems and methods for conducting financial transactions over a network
US7526486B2 (en) 2006-05-22 2009-04-28 Initiate Systems, Inc. Method and system for indexing information about entities with respect to hierarchies
US7747494B1 (en) * 2006-05-24 2010-06-29 Pravin Kothari Non-determinative risk simulation
US7752125B1 (en) * 2006-05-24 2010-07-06 Pravin Kothari Automated enterprise risk assessment
EP2030134A4 (en) * 2006-06-02 2010-06-23 Initiate Systems Inc A system and method for automatic weight generation for probabilistic matching
US20080015977A1 (en) * 2006-06-14 2008-01-17 Curry Edith L Methods of deterring fraud and other improper behaviors within an organization
US7881535B1 (en) 2006-06-29 2011-02-01 Capital One Financial Corporation System and method for managing statistical models
WO2008005526A2 (en) * 2006-07-06 2008-01-10 Fair Isaac Corporation Auto adaptive anomaly detection system for streams
MX2009002148A (en) 2006-08-29 2009-05-12 Visa Int Service Ass Method and system for processing internet purchase transactions.
US7698268B1 (en) * 2006-09-15 2010-04-13 Initiate Systems, Inc. Method and system for filtering false positives
US7685093B1 (en) * 2006-09-15 2010-03-23 Initiate Systems, Inc. Method and system for comparing attributes such as business names
US8356009B2 (en) * 2006-09-15 2013-01-15 International Business Machines Corporation Implementation defined segments for relational database systems
US8027439B2 (en) * 2006-09-18 2011-09-27 Fair Isaac Corporation Self-calibrating fraud detection
US20080086342A1 (en) * 2006-10-09 2008-04-10 Curry Edith L Methods of assessing fraud risk, and deterring, detecting, and mitigating fraud, within an organization
US20080091445A1 (en) * 2006-10-16 2008-04-17 Matthew Mihic Method and system for dynamic social networking based on similar travel itineraries
US20080103800A1 (en) * 2006-10-25 2008-05-01 Domenikos Steven D Identity Protection
US8359278B2 (en) 2006-10-25 2013-01-22 IndentityTruth, Inc. Identity protection
US7657497B2 (en) 2006-11-07 2010-02-02 Ebay Inc. Online fraud prevention using genetic algorithm solution
US8025220B2 (en) * 2006-11-10 2011-09-27 Fair Isaac Corporation Cardholder localization based on transaction data
US8160977B2 (en) * 2006-12-11 2012-04-17 Poulin Christian D Collaborative predictive model building
US9779556B1 (en) 2006-12-27 2017-10-03 Stamps.Com Inc. System and method for identifying and preventing on-line fraud
US7711684B2 (en) * 2006-12-28 2010-05-04 Ebay Inc. Collaborative content evaluation
US8359339B2 (en) * 2007-02-05 2013-01-22 International Business Machines Corporation Graphical user interface for configuration of an algorithm for the matching of data records
US8346691B1 (en) 2007-02-20 2013-01-01 Sas Institute Inc. Computer-implemented semi-supervised learning systems and methods
US8015133B1 (en) 2007-02-20 2011-09-06 Sas Institute Inc. Computer-implemented modeling systems and methods for analyzing and predicting computer network intrusions
US8190512B1 (en) 2007-02-20 2012-05-29 Sas Institute Inc. Computer-implemented clustering systems and methods for action determination
US8930331B2 (en) 2007-02-21 2015-01-06 Palantir Technologies Providing unique views of data based on changes or rules
US8032449B2 (en) * 2007-03-08 2011-10-04 Soft Route Corporation Method of processing online payments with fraud analysis and management system
US7539644B2 (en) * 2007-03-08 2009-05-26 Softroute Corporation Method of processing online payments with fraud analysis and management system
US8694374B1 (en) * 2007-03-14 2014-04-08 Google Inc. Detecting click spam
US9185123B2 (en) 2008-02-12 2015-11-10 Finsphere Corporation System and method for mobile identity protection for online user authentication
US8280348B2 (en) 2007-03-16 2012-10-02 Finsphere Corporation System and method for identity protection using mobile device signaling network derived location pattern recognition
US8515926B2 (en) 2007-03-22 2013-08-20 International Business Machines Corporation Processing related data from information sources
US8423514B2 (en) * 2007-03-29 2013-04-16 International Business Machines Corporation Service provisioning
WO2008121700A1 (en) * 2007-03-29 2008-10-09 Initiate Systems, Inc. Method and system for managing entities
US8429220B2 (en) * 2007-03-29 2013-04-23 International Business Machines Corporation Data exchange among data sources
US8321393B2 (en) * 2007-03-29 2012-11-27 International Business Machines Corporation Parsing information in data records and in different languages
US20080262961A1 (en) * 2007-04-17 2008-10-23 First Data Corporation Merchant Credit Risk Monitoring
US8725597B2 (en) * 2007-04-25 2014-05-13 Google Inc. Merchant scoring system and transactional database
US10769290B2 (en) * 2007-05-11 2020-09-08 Fair Isaac Corporation Systems and methods for fraud detection via interactive link analysis
US20080283593A1 (en) * 2007-05-18 2008-11-20 Bank Of America Corporation Compromised Account Detection
JP2009048402A (en) * 2007-08-20 2009-03-05 Fujitsu Ltd Application procedure illegal risk evaluation device
US8713434B2 (en) * 2007-09-28 2014-04-29 International Business Machines Corporation Indexing, relating and managing information about entities
EP2198374A4 (en) * 2007-09-28 2013-07-17 Ibm Method and system for associating data records in multiple languages
WO2009042941A1 (en) 2007-09-28 2009-04-02 Initiate Systems, Inc. Method and system for analysis of a system for matching data records
US8121957B1 (en) * 2007-10-01 2012-02-21 Google Inc. Discrete verification of payment information
US7653593B2 (en) 2007-11-08 2010-01-26 Equifax, Inc. Macroeconomic-adjusted credit risk score systems and methods
US8622308B1 (en) 2007-12-31 2014-01-07 Jpmorgan Chase Bank, N.A. System and method for processing transactions using a multi-account transactions device
US8078528B1 (en) 2008-02-21 2011-12-13 Jpmorgan Chase Bank, N.A. System and method for providing borrowing schemes
US10510025B2 (en) * 2008-02-29 2019-12-17 Fair Isaac Corporation Adaptive fraud detection
US8255971B1 (en) * 2008-03-03 2012-08-28 Jpmorgan Chase Bank, N.A. Authentication system and method
CA2757290C (en) 2008-04-01 2020-12-15 Leap Marketing Technologies Inc. Systems and methods for implementing and tracking identification tests
US9842204B2 (en) 2008-04-01 2017-12-12 Nudata Security Inc. Systems and methods for assessing security risk
US8521631B2 (en) 2008-05-29 2013-08-27 Sas Institute Inc. Computer-implemented systems and methods for loan evaluation using a credit assessment framework
US10410220B2 (en) 2008-06-12 2019-09-10 Guardian Analytics, Inc. Fraud detection and analysis system
US20090327107A1 (en) * 2008-06-30 2009-12-31 Raghav Lal Consumer spending threshold evaluation
US9009082B1 (en) 2008-06-30 2015-04-14 Amazon Technologies, Inc. Assessing user-supplied evaluations
US20100129780A1 (en) * 2008-09-12 2010-05-27 Nike, Inc. Athletic performance rating system
US10747952B2 (en) 2008-09-15 2020-08-18 Palantir Technologies, Inc. Automatic creation and server push of multiple distinct drafts
US8892868B1 (en) 2008-09-30 2014-11-18 Amazon Technologies, Inc. Hardening tokenization security and key rotation
US9053480B1 (en) * 2008-09-30 2015-06-09 Amazon Technologies, Inc. Secure validation using hardware security modules
US9563889B2 (en) * 2009-02-25 2017-02-07 General Electric Company Method and apparatus for secure wireless point of sale transactions
US9112850B1 (en) 2009-03-25 2015-08-18 The 41St Parameter, Inc. Systems and methods of sharing information through a tag-based consortium
US8204833B2 (en) * 2009-05-27 2012-06-19 Softroute Corporation Method for fingerprinting and identifying internet users
US8600873B2 (en) * 2009-05-28 2013-12-03 Visa International Service Association Managed real-time transaction fraud analysis and decisioning
US10290053B2 (en) 2009-06-12 2019-05-14 Guardian Analytics, Inc. Fraud detection and analysis
US11797997B2 (en) * 2009-07-07 2023-10-24 Visa International Service Association Data verification in transactions in distributed network
US20120130898A1 (en) * 2009-07-07 2012-05-24 Finsphere, Inc. Mobile directory number and email verification of financial transactions
US8380591B1 (en) * 2009-07-10 2013-02-19 United Services Automobile Association (Usaa) System and method for providing warning and protection for bill payments
US20110016041A1 (en) * 2009-07-14 2011-01-20 Scragg Ernest M Triggering Fraud Rules for Financial Transactions
US20110016052A1 (en) * 2009-07-16 2011-01-20 Scragg Ernest M Event Tracking and Velocity Fraud Rules for Financial Transactions
US8752142B2 (en) 2009-07-17 2014-06-10 American Express Travel Related Services Company, Inc. Systems, methods, and computer program products for adapting the security measures of a communication network based on feedback
US8751375B2 (en) * 2009-08-31 2014-06-10 Bank Of America Corporation Event processing for detection of suspicious financial activity
US10242540B2 (en) * 2009-09-02 2019-03-26 Fair Isaac Corporation Visualization for payment card transaction fraud analysis
US8326751B2 (en) * 2009-09-30 2012-12-04 Zynga Inc. Apparatuses,methods and systems for a trackable virtual currencies platform
US8214285B2 (en) * 2009-10-05 2012-07-03 Cybersource Corporation Real time adaptive control of transaction review rate score curve
US20110099101A1 (en) * 2009-10-26 2011-04-28 Bank Of America Corporation Automated validation reporting for risk models
US8805737B1 (en) * 2009-11-02 2014-08-12 Sas Institute Inc. Computer-implemented multiple entity dynamic summarization systems and methods
US9756076B2 (en) 2009-12-17 2017-09-05 American Express Travel Related Services Company, Inc. Dynamically reacting policies and protections for securing mobile financial transactions
US8621636B2 (en) 2009-12-17 2013-12-31 American Express Travel Related Services Company, Inc. Systems, methods, and computer program products for collecting and reporting sensor data in a communication network
US20110167001A1 (en) * 2010-01-07 2011-07-07 The Western Union Company Geodictionary
US8489499B2 (en) 2010-01-13 2013-07-16 Corelogic Solutions, Llc System and method of detecting and assessing multiple types of risks related to mortgage lending
US8650129B2 (en) * 2010-01-20 2014-02-11 American Express Travel Related Services Company, Inc. Dynamically reacting policies and protections for securing mobile financial transaction data in transit
US20110225076A1 (en) 2010-03-09 2011-09-15 Google Inc. Method and system for detecting fraudulent internet merchants
US8626663B2 (en) 2010-03-23 2014-01-07 Visa International Service Association Merchant fraud risk score
US9652802B1 (en) 2010-03-24 2017-05-16 Consumerinfo.Com, Inc. Indirect monitoring and reporting of a user's credit data
US20110238516A1 (en) * 2010-03-26 2011-09-29 Securefraud Inc. E-commerce threat detection
US9171306B1 (en) 2010-03-29 2015-10-27 Bank Of America Corporation Risk-based transaction authentication
US10360625B2 (en) 2010-06-22 2019-07-23 American Express Travel Related Services Company, Inc. Dynamically adaptive policy management for securing mobile financial transactions
US8924296B2 (en) 2010-06-22 2014-12-30 American Express Travel Related Services Company, Inc. Dynamic pairing system for securing a trusted communication channel
US8850539B2 (en) 2010-06-22 2014-09-30 American Express Travel Related Services Company, Inc. Adaptive policies and protections for securing financial transaction data at rest
US8412563B2 (en) * 2010-07-02 2013-04-02 Fis Financial Compliance Solutions, Llc Method and system for analyzing and optimizing distribution of work from a plurality of queues
US8554631B1 (en) 2010-07-02 2013-10-08 Jpmorgan Chase Bank, N.A. Method and system for determining point of sale authorization
US9342832B2 (en) 2010-08-12 2016-05-17 Visa International Service Association Securing external systems with account token substitution
US8326760B2 (en) * 2010-09-13 2012-12-04 Cybersource Corporation Computer-based collective intelligence recommendations for transaction review
US20120109821A1 (en) * 2010-10-29 2012-05-03 Jesse Barbour System, method and computer program product for real-time online transaction risk and fraud analytics and management
GB201020973D0 (en) * 2010-12-10 2011-01-26 Panaplay Ltd Risk management system and method
EP3462317A1 (en) 2011-02-18 2019-04-03 CSidentity Corporation System and methods for identifying compromised personally identifiable information on the internet
US9449288B2 (en) 2011-05-20 2016-09-20 Deem, Inc. Travel services search
US8661038B1 (en) 2011-05-31 2014-02-25 Intuit Inc. Method and system for utilizing location data for automatic categorization of financial transactions
EP3439267A1 (en) 2011-06-03 2019-02-06 UC Group Limited Systems and methods for managing chargeback requests
US20120316990A1 (en) * 2011-06-09 2012-12-13 Google Inc. Evaluating Merchant Trustworthiness
US9092482B2 (en) 2013-03-14 2015-07-28 Palantir Technologies, Inc. Fair scheduling for mixed-query loads
US8799240B2 (en) 2011-06-23 2014-08-05 Palantir Technologies, Inc. System and method for investigating large amounts of data
US9547693B1 (en) 2011-06-23 2017-01-17 Palantir Technologies Inc. Periodic database search manager for multiple data sources
US20130018791A1 (en) * 2011-07-14 2013-01-17 Bank Of America Corporation Fraud data exchange system
US10176533B2 (en) * 2011-07-25 2019-01-08 Prevedere Inc. Interactive chart utilizing shifting control to render shifting of time domains of data series
US8924393B1 (en) 2011-07-28 2014-12-30 Intuit Inc. Method and system for improving automatic categorization of financial transactions
US8732574B2 (en) 2011-08-25 2014-05-20 Palantir Technologies, Inc. System and method for parameterizing documents for automatic workflow generation
US8504542B2 (en) 2011-09-02 2013-08-06 Palantir Technologies, Inc. Multi-row transactions
US8819793B2 (en) 2011-09-20 2014-08-26 Csidentity Corporation Systems and methods for secure and efficient enrollment into a federation which utilizes a biometric repository
US20130073319A1 (en) * 2011-09-21 2013-03-21 Corelogic Solutions, Llc Apparatus, method and computer program product for determining composite hazard index
US8996417B1 (en) 2011-10-13 2015-03-31 Intuit Inc. Method and system for automatically obtaining and categorizing cash transaction data using a mobile computing system
US8768866B2 (en) 2011-10-21 2014-07-01 Sas Institute Inc. Computer-implemented systems and methods for forecasting and estimation using grid regression
US11030562B1 (en) 2011-10-31 2021-06-08 Consumerinfo.Com, Inc. Pre-data breach monitoring
US10424011B2 (en) * 2011-11-02 2019-09-24 Gain Credit Holdings, Inc Systems and methods for shared lending risk
US10754913B2 (en) 2011-11-15 2020-08-25 Tapad, Inc. System and method for analyzing user device information
WO2013082190A1 (en) * 2011-11-28 2013-06-06 Visa International Service Association Transaction security graduated seasoning and risk shifting apparatuses, methods and systems
US8478688B1 (en) * 2011-12-19 2013-07-02 Emc Corporation Rapid transaction processing
CA2800455A1 (en) * 2011-12-29 2013-06-29 Equifax, Inc. Determining a personalized fusion score
US10223710B2 (en) 2013-01-04 2019-03-05 Visa International Service Association Wearable intelligent vision device apparatuses, methods and systems
US8660984B1 (en) 2012-01-13 2014-02-25 Intuit Inc. Method and system for automatic categorization of check-based financial transactions
US20130185180A1 (en) * 2012-01-18 2013-07-18 Bank Of America Corporation Determining the investigation priority of potential suspicious events within a financial institution
CN103220662B (en) * 2012-01-20 2016-01-20 腾讯科技(深圳)有限公司 A kind of processing method of application program and mobile terminal
US8655773B1 (en) * 2012-01-26 2014-02-18 Intuit Inc. Geo-location based underwriting
US9811827B2 (en) 2012-02-28 2017-11-07 Google Inc. System and method for providing transaction verification
US9633201B1 (en) 2012-03-01 2017-04-25 The 41St Parameter, Inc. Methods and systems for fraud containment
US20130232045A1 (en) * 2012-03-04 2013-09-05 Oracle International Corporation Automatic Detection Of Fraud And Error Using A Vector-Cluster Model
US10970688B2 (en) 2012-03-07 2021-04-06 Early Warning Services, Llc System and method for transferring funds
US10395247B2 (en) 2012-03-07 2019-08-27 Early Warning Services, Llc Systems and methods for facilitating a secure transaction at a non-financial institution system
US20130238488A1 (en) 2012-03-07 2013-09-12 Clearxchange, Llc System and method for transferring funds
US11593800B2 (en) 2012-03-07 2023-02-28 Early Warning Services, Llc System and method for transferring funds
US10395223B2 (en) 2012-03-07 2019-08-27 Early Warning Services, Llc System and method for transferring funds
US8855377B1 (en) 2012-03-09 2014-10-07 Intuit Inc. Method and system for semi-automated setup of accounts within a data management system
US20130346294A1 (en) * 2012-03-21 2013-12-26 Patrick Faith Risk manager optimizer
US9521551B2 (en) 2012-03-22 2016-12-13 The 41St Parameter, Inc. Methods and systems for persistent cross-application mobile device identification
EP2845159A4 (en) 2012-04-18 2015-11-11 Mastercard International Inc Systems and methods for managing transactions for a merchant
US20130282583A1 (en) * 2012-04-20 2013-10-24 Cory H. Siddens Fraud detection system rule profile interaction
US9635067B2 (en) 2012-04-23 2017-04-25 Verint Americas Inc. Tracing and asynchronous communication network and routing method
US20130282844A1 (en) 2012-04-23 2013-10-24 Contact Solutions LLC Apparatus and methods for multi-mode asynchronous communication
US8938462B2 (en) * 2012-04-25 2015-01-20 International Business Machines Corporation Adaptively assessing object relevance based on dynamic user properties
US10592978B1 (en) * 2012-06-29 2020-03-17 EMC IP Holding Company LLC Methods and apparatus for risk-based authentication between two servers on behalf of a user
US8856923B1 (en) * 2012-06-29 2014-10-07 Emc Corporation Similarity-based fraud detection in adaptive authentication systems
US20140039974A1 (en) * 2012-08-01 2014-02-06 Mastercard International Incorporated System and method for using credit/debit card transaction data as a measure of customer satisfaction with a merchant
EP2880619A1 (en) 2012-08-02 2015-06-10 The 41st Parameter, Inc. Systems and methods for accessing records via derivative locators
US8930267B1 (en) * 2012-08-27 2015-01-06 Jpmorgan Chase Bank, N.A. Automated transactions clearing system and method
US9368116B2 (en) 2012-09-07 2016-06-14 Verint Systems Ltd. Speaker separation in diarization
US8688573B1 (en) * 2012-10-16 2014-04-01 Intuit Inc. Method and system for identifying a merchant payee associated with a cash transaction
US9348677B2 (en) 2012-10-22 2016-05-24 Palantir Technologies Inc. System and method for batch evaluation programs
US20140122305A1 (en) * 2012-10-25 2014-05-01 Global Edge Llc Purchase card management
US9953321B2 (en) * 2012-10-30 2018-04-24 Fair Isaac Corporation Card fraud detection utilizing real-time identification of merchant test sites
US20140129288A1 (en) * 2012-11-06 2014-05-08 Dna Response Inc. Systems and Methods for Detecting and Eliminating Marketing of Fraudulent Goods
WO2014078569A1 (en) 2012-11-14 2014-05-22 The 41St Parameter, Inc. Systems and methods of global identification
US10134400B2 (en) 2012-11-21 2018-11-20 Verint Systems Ltd. Diarization using acoustic labeling
US9858571B2 (en) * 2013-01-02 2018-01-02 Mastercard International Incorporated Methods and systems for mitigating fraud losses during a payment card transaction
WO2014111540A1 (en) 2013-01-21 2014-07-24 Ides Technologies Sa System and method for characterizing financial messages
US10438228B2 (en) 2013-01-30 2019-10-08 Walmart Apollo, Llc Systems and methods for price matching and comparison
US10572892B2 (en) 2013-01-30 2020-02-25 Walmart Apollo, Llc Price comparison systems and methods
US20140214518A1 (en) * 2013-01-30 2014-07-31 Wal-Mart Stores, Inc. System and method for price matching and comparison
US9123086B1 (en) 2013-01-31 2015-09-01 Palantir Technologies, Inc. Automatically generating event objects from images
US20140250011A1 (en) 2013-03-01 2014-09-04 Lance Weber Account type detection for fraud risk
US20140258119A1 (en) * 2013-03-06 2014-09-11 Laure Canis Fraud Decision Processing System and Method
CN103209174B (en) * 2013-03-12 2016-03-30 华为技术有限公司 A kind of data prevention method, Apparatus and system
US9098852B1 (en) * 2013-03-14 2015-08-04 Jpmorgan Chase Bank, N.A. Method and system for monitoring and detecting fraud in targeted benefits
US8812387B1 (en) 2013-03-14 2014-08-19 Csidentity Corporation System and method for identifying related credit inquiries
US9594907B2 (en) 2013-03-14 2017-03-14 Sas Institute Inc. Unauthorized activity detection and classification
US9231979B2 (en) 2013-03-14 2016-01-05 Sas Institute Inc. Rule optimization for classification and detection
US10037314B2 (en) 2013-03-14 2018-07-31 Palantir Technologies, Inc. Mobile reports
US8868486B2 (en) 2013-03-15 2014-10-21 Palantir Technologies Inc. Time-sensitive cube
US9965937B2 (en) 2013-03-15 2018-05-08 Palantir Technologies Inc. External malware data item clustering and analysis
US8788405B1 (en) 2013-03-15 2014-07-22 Palantir Technologies, Inc. Generating data clusters with customizable analysis strategies
US8917274B2 (en) 2013-03-15 2014-12-23 Palantir Technologies Inc. Event matrix based on integrated data
US10275778B1 (en) 2013-03-15 2019-04-30 Palantir Technologies Inc. Systems and user interfaces for dynamic and interactive investigation based on automatic malfeasance clustering of related data in various data structures
US8937619B2 (en) 2013-03-15 2015-01-20 Palantir Technologies Inc. Generating an object time series from data objects
US8909656B2 (en) 2013-03-15 2014-12-09 Palantir Technologies Inc. Filter chains with associated multipath views for exploring large data sets
CN104079525B (en) * 2013-03-25 2015-11-11 腾讯科技(深圳)有限公司 A kind ofly prevent plug-in method and server
US10692087B2 (en) * 2013-04-03 2020-06-23 Blackhawk Network, Inc. Electronic financial service risk evaluation
US20140316960A1 (en) * 2013-04-23 2014-10-23 Bank Of America Corporation Merchant bank tool
US8799799B1 (en) 2013-05-07 2014-08-05 Palantir Technologies Inc. Interactive geospatial map
US9811830B2 (en) 2013-07-03 2017-11-07 Google Inc. Method, medium, and system for online fraud prevention based on user physical location data
US9460722B2 (en) 2013-07-17 2016-10-04 Verint Systems Ltd. Blind diarization of recorded calls with arbitrary number of speakers
US9984706B2 (en) 2013-08-01 2018-05-29 Verint Systems Ltd. Voice activity detection using a soft decision mechanism
US8713467B1 (en) 2013-08-09 2014-04-29 Palantir Technologies, Inc. Context-sensitive views
US10902327B1 (en) 2013-08-30 2021-01-26 The 41St Parameter, Inc. System and method for device identification and uniqueness
US20150081494A1 (en) * 2013-09-17 2015-03-19 Sap Ag Calibration of strategies for fraud detection
US20150088613A1 (en) * 2013-09-23 2015-03-26 Comdata Network, Inc. Systems, methods, and computer program products for managing fuel costs
US8938686B1 (en) 2013-10-03 2015-01-20 Palantir Technologies Inc. Systems and methods for analyzing performance of an entity
US20150106265A1 (en) * 2013-10-11 2015-04-16 Telesign Corporation System and methods for processing a communication number for fraud prevention
US8924872B1 (en) 2013-10-18 2014-12-30 Palantir Technologies Inc. Overview user interface of emergency call data of a law enforcement agency
US9116975B2 (en) 2013-10-18 2015-08-25 Palantir Technologies Inc. Systems and user interfaces for dynamic and interactive simultaneous querying of multiple data stores
US9021384B1 (en) 2013-11-04 2015-04-28 Palantir Technologies Inc. Interactive vehicle information map
US8868537B1 (en) 2013-11-11 2014-10-21 Palantir Technologies, Inc. Simple web search
US9058626B1 (en) 2013-11-13 2015-06-16 Jpmorgan Chase Bank, N.A. System and method for financial services device usage
US9105000B1 (en) 2013-12-10 2015-08-11 Palantir Technologies Inc. Aggregating data from a plurality of data sources
US10025834B2 (en) 2013-12-16 2018-07-17 Palantir Technologies Inc. Methods and systems for analyzing entity performance
US10579647B1 (en) 2013-12-16 2020-03-03 Palantir Technologies Inc. Methods and systems for analyzing entity performance
US9552615B2 (en) * 2013-12-20 2017-01-24 Palantir Technologies Inc. Automated database analysis to detect malfeasance
US10356032B2 (en) 2013-12-26 2019-07-16 Palantir Technologies Inc. System and method for detecting confidential information emails
US8832832B1 (en) 2014-01-03 2014-09-09 Palantir Technologies Inc. IP reputation
US9218410B2 (en) 2014-02-06 2015-12-22 Contact Solutions LLC Systems, apparatuses and methods for communication flow modification
US20150235219A1 (en) * 2014-02-19 2015-08-20 Bank Of America Corporation Item/value based risk mitigating transaction authorization
US20150235220A1 (en) * 2014-02-19 2015-08-20 Bank Of America Corporation Location based risk mitigating transaction authorization
US9483162B2 (en) 2014-02-20 2016-11-01 Palantir Technologies Inc. Relationship visualizations
US9009827B1 (en) 2014-02-20 2015-04-14 Palantir Technologies Inc. Security sharing system
US20150242857A1 (en) * 2014-02-24 2015-08-27 Bank Of America Corporation Transaction Risk Assessment Aggregation
US9727376B1 (en) 2014-03-04 2017-08-08 Palantir Technologies, Inc. Mobile tasks
US20150262184A1 (en) * 2014-03-12 2015-09-17 Microsoft Corporation Two stage risk model building and evaluation
US8924429B1 (en) 2014-03-18 2014-12-30 Palantir Technologies Inc. Determining and extracting changed data from a data source
US10896421B2 (en) 2014-04-02 2021-01-19 Brighterion, Inc. Smart retail analytics and commercial messaging
US9857958B2 (en) 2014-04-28 2018-01-02 Palantir Technologies Inc. Systems and user interfaces for dynamic and interactive access of, investigation of, and analysis of data objects stored in one or more databases
US10672078B1 (en) * 2014-05-19 2020-06-02 Allstate Insurance Company Scoring of insurance data
US9396332B2 (en) 2014-05-21 2016-07-19 Microsoft Technology Licensing, Llc Risk assessment modeling
US9535974B1 (en) 2014-06-30 2017-01-03 Palantir Technologies Inc. Systems and methods for identifying key phrase clusters within documents
US9619557B2 (en) 2014-06-30 2017-04-11 Palantir Technologies, Inc. Systems and methods for key phrase characterization of documents
US9256664B2 (en) 2014-07-03 2016-02-09 Palantir Technologies Inc. System and method for news events detection and visualization
US10572496B1 (en) 2014-07-03 2020-02-25 Palantir Technologies Inc. Distributed workflow system and database with access controls for city resiliency
US9202249B1 (en) 2014-07-03 2015-12-01 Palantir Technologies Inc. Data item clustering and analysis
US9118714B1 (en) * 2014-07-23 2015-08-25 Lookingglass Cyber Solutions, Inc. Apparatuses, methods and systems for a cyber threat visualization and editing user interface
US20150066771A1 (en) 2014-08-08 2015-03-05 Brighterion, Inc. Fast access vectors in real-time behavioral profiling
US20150032589A1 (en) 2014-08-08 2015-01-29 Brighterion, Inc. Artificial intelligence fraud management solution
US20160055427A1 (en) 2014-10-15 2016-02-25 Brighterion, Inc. Method for providing data science, artificial intelligence and machine learning as-a-service
US20150339673A1 (en) 2014-10-28 2015-11-26 Brighterion, Inc. Method for detecting merchant data breaches with a computer network server
US9454281B2 (en) 2014-09-03 2016-09-27 Palantir Technologies Inc. System for providing dynamic linked panels in user interface
US9501851B2 (en) 2014-10-03 2016-11-22 Palantir Technologies Inc. Time-series analysis system
US9767172B2 (en) 2014-10-03 2017-09-19 Palantir Technologies Inc. Data aggregation and analysis system
US10091312B1 (en) 2014-10-14 2018-10-02 The 41St Parameter, Inc. Data structures for intelligently resolving deterministic and probabilistic device identifiers to device profiles and/or groups
US20160063502A1 (en) 2014-10-15 2016-03-03 Brighterion, Inc. Method for improving operating profits with better automated decision making with artificial intelligence
US20160071017A1 (en) 2014-10-15 2016-03-10 Brighterion, Inc. Method of operating artificial intelligence machines to improve predictive model training and performance
US10546099B2 (en) 2014-10-15 2020-01-28 Brighterion, Inc. Method of personalizing, individualizing, and automating the management of healthcare fraud-waste-abuse to unique individual healthcare providers
US20160078367A1 (en) 2014-10-15 2016-03-17 Brighterion, Inc. Data clean-up method for improving predictive model training
US11080709B2 (en) 2014-10-15 2021-08-03 Brighterion, Inc. Method of reducing financial losses in multiple payment channels upon a recognition of fraud first appearing in any one payment channel
US9984133B2 (en) 2014-10-16 2018-05-29 Palantir Technologies Inc. Schematic and database linking system
US10290001B2 (en) * 2014-10-28 2019-05-14 Brighterion, Inc. Data breach detection
US10339527B1 (en) 2014-10-31 2019-07-02 Experian Information Solutions, Inc. System and architecture for electronic fraud detection
US9229952B1 (en) 2014-11-05 2016-01-05 Palantir Technologies, Inc. History preserving data pipeline system and method
US9043894B1 (en) 2014-11-06 2015-05-26 Palantir Technologies Inc. Malicious software detection in a computing system
US20160148092A1 (en) * 2014-11-20 2016-05-26 Mastercard International Incorporated Systems and methods for determining activity level at a merchant location by leveraging real-time transaction data
JP6534255B2 (en) * 2014-11-26 2019-06-26 かっこ株式会社 Fraudulent transaction detection system
US11042880B1 (en) 2014-12-17 2021-06-22 EMC IP Holding Company LLC Authenticating users in the presence of small transaction volumes
US9910882B2 (en) 2014-12-19 2018-03-06 International Business Machines Corporation Isolation anomaly quantification through heuristical pattern detection
US9922071B2 (en) 2014-12-19 2018-03-20 International Business Machines Corporation Isolation anomaly quantification through heuristical pattern detection
US10552994B2 (en) 2014-12-22 2020-02-04 Palantir Technologies Inc. Systems and interactive user interfaces for dynamic retrieval, analysis, and triage of data items
US9348920B1 (en) 2014-12-22 2016-05-24 Palantir Technologies Inc. Concept indexing among database of documents using machine learning techniques
US10362133B1 (en) 2014-12-22 2019-07-23 Palantir Technologies Inc. Communication data processing architecture
US9367872B1 (en) 2014-12-22 2016-06-14 Palantir Technologies Inc. Systems and user interfaces for dynamic and interactive investigation of bad actor behavior based on automatic clustering of related data in various data structures
US9335911B1 (en) 2014-12-29 2016-05-10 Palantir Technologies Inc. Interactive user interface for dynamic data analysis exploration and query processing
US9817563B1 (en) 2014-12-29 2017-11-14 Palantir Technologies Inc. System and method of generating data points from one or more data stores of data items for chart creation and manipulation
US9870205B1 (en) 2014-12-29 2018-01-16 Palantir Technologies Inc. Storing logical units of program code generated using a dynamic programming notebook user interface
US9166881B1 (en) 2014-12-31 2015-10-20 Contact Solutions LLC Methods and apparatus for adaptive bandwidth-based communication management
US10372879B2 (en) 2014-12-31 2019-08-06 Palantir Technologies Inc. Medical claims lead summary report generation
US11302426B1 (en) 2015-01-02 2022-04-12 Palantir Technologies Inc. Unified data interface and system
CN105844526A (en) * 2015-01-14 2016-08-10 阿里巴巴集团控股有限公司 Networked transaction risk identification method and networked transaction risk identification device based on computer system
US9875743B2 (en) 2015-01-26 2018-01-23 Verint Systems Ltd. Acoustic signature building for a speaker from multiple sessions
US9727560B2 (en) 2015-02-25 2017-08-08 Palantir Technologies Inc. Systems and methods for organizing and identifying documents via hierarchies and dimensions of tags
EP3070622A1 (en) 2015-03-16 2016-09-21 Palantir Technologies, Inc. Interactive user interfaces for location-based data analysis
US9886467B2 (en) 2015-03-19 2018-02-06 Plantir Technologies Inc. System and method for comparing and visualizing data entities and data entity series
US10878387B2 (en) 2015-03-23 2020-12-29 Early Warning Services, Llc Real-time determination of funds availability for checks and ACH items
US10832246B2 (en) 2015-03-23 2020-11-10 Early Warning Services, Llc Payment real-time funds availability
US10839359B2 (en) 2015-03-23 2020-11-17 Early Warning Services, Llc Payment real-time funds availability
US10748127B2 (en) 2015-03-23 2020-08-18 Early Warning Services, Llc Payment real-time funds availability
US10769606B2 (en) 2015-03-23 2020-09-08 Early Warning Services, Llc Payment real-time funds availability
EP3292533A4 (en) * 2015-05-05 2018-03-14 Zeta Global Corp. Predictive modeling and analytics integration plataform
US10103953B1 (en) 2015-05-12 2018-10-16 Palantir Technologies Inc. Methods and systems for analyzing entity performance
US11423404B2 (en) * 2015-05-13 2022-08-23 Mastercard International Incorporated System and methods for enhanced approval of a payment transaction
PH12015000166A1 (en) * 2015-05-15 2016-11-21 James D Griffin Method and system for fraud detection and compliance management
US10540608B1 (en) * 2015-05-22 2020-01-21 Amazon Technologies, Inc. Dynamically scaled training fleets for machine learning
US11030622B2 (en) * 2015-06-11 2021-06-08 Early Warning Services, Llc Card systems and methods
US10628834B1 (en) * 2015-06-16 2020-04-21 Palantir Technologies Inc. Fraud lead detection system for efficiently processing database-stored data and automatically generating natural language explanatory information of system results for display in interactive user interfaces
US11151468B1 (en) 2015-07-02 2021-10-19 Experian Information Solutions, Inc. Behavior analysis using distributed representations of event data
US11037121B2 (en) 2015-07-21 2021-06-15 Early Warning Services, Llc Secure real-time transactions
US11151523B2 (en) 2015-07-21 2021-10-19 Early Warning Services, Llc Secure transactions with offline device
US11157884B2 (en) 2015-07-21 2021-10-26 Early Warning Services, Llc Secure transactions with offline device
US10438175B2 (en) 2015-07-21 2019-10-08 Early Warning Services, Llc Secure real-time payment transactions
US10963856B2 (en) 2015-07-21 2021-03-30 Early Warning Services, Llc Secure real-time transactions
US11037122B2 (en) 2015-07-21 2021-06-15 Early Warning Services, Llc Secure real-time transactions
US10956888B2 (en) 2015-07-21 2021-03-23 Early Warning Services, Llc Secure real-time transactions
US11062290B2 (en) 2015-07-21 2021-07-13 Early Warning Services, Llc Secure real-time transactions
US11386410B2 (en) 2015-07-21 2022-07-12 Early Warning Services, Llc Secure transactions with offline device
US11151522B2 (en) 2015-07-21 2021-10-19 Early Warning Services, Llc Secure transactions with offline device
US10970695B2 (en) 2015-07-21 2021-04-06 Early Warning Services, Llc Secure real-time transactions
US9392008B1 (en) * 2015-07-23 2016-07-12 Palantir Technologies Inc. Systems and methods for identifying information related to payment card breaches
US9454785B1 (en) 2015-07-30 2016-09-27 Palantir Technologies Inc. Systems and user interfaces for holistic, data-driven investigation of bad actor behavior based on clustering and scoring of related data
US10671915B2 (en) 2015-07-31 2020-06-02 Brighterion, Inc. Method for calling for preemptive maintenance and for equipment failure prevention
US9996595B2 (en) 2015-08-03 2018-06-12 Palantir Technologies, Inc. Providing full data provenance visualization for versioned datasets
WO2017024248A1 (en) 2015-08-06 2017-02-09 Contact Solutions LLC Tracing and asynchronous communication network and routing method
US9456000B1 (en) 2015-08-06 2016-09-27 Palantir Technologies Inc. Systems, methods, user interfaces, and computer-readable media for investigating potential malicious communications
US10489391B1 (en) 2015-08-17 2019-11-26 Palantir Technologies Inc. Systems and methods for grouping and enriching data items accessed from one or more databases for presentation in a user interface
US9600146B2 (en) 2015-08-17 2017-03-21 Palantir Technologies Inc. Interactive geospatial map
US10853378B1 (en) 2015-08-25 2020-12-01 Palantir Technologies Inc. Electronic note management via a connected entity graph
US11150917B2 (en) 2015-08-26 2021-10-19 Palantir Technologies Inc. System for data aggregation and analysis of data from a plurality of data sources
US9485265B1 (en) 2015-08-28 2016-11-01 Palantir Technologies Inc. Malicious activity detection system capable of efficiently processing data accessed from databases and generating alerts for display in interactive user interfaces
US10706434B1 (en) 2015-09-01 2020-07-07 Palantir Technologies Inc. Methods and systems for determining location information
US9576015B1 (en) 2015-09-09 2017-02-21 Palantir Technologies, Inc. Domain-specific language for dataset transformations
US10013539B1 (en) 2015-09-25 2018-07-03 EMC IP Holding Company LLC Rapid device identification among multiple users
US10296617B1 (en) 2015-10-05 2019-05-21 Palantir Technologies Inc. Searches of highly structured data
US20170186083A1 (en) * 2015-12-07 2017-06-29 Paypal, Inc. Data mining a transaction history data structure
US9542446B1 (en) 2015-12-17 2017-01-10 Palantir Technologies, Inc. Automatic generation of composite datasets based on hierarchical fields
US9823818B1 (en) 2015-12-29 2017-11-21 Palantir Technologies Inc. Systems and interactive user interfaces for automatic generation of temporal representation of data objects
US9612723B1 (en) 2015-12-30 2017-04-04 Palantir Technologies Inc. Composite graphical interface with shareable data-objects
US10489840B2 (en) 2016-01-22 2019-11-26 Walmart Apollo, Llc System, method, and non-transitory computer-readable storage media related to providing real-time price matching and time synchronization encryption
US20170262853A1 (en) * 2016-03-14 2017-09-14 Mastercard International Incorporated Method and system for biometric confirmation of suspect transactions
US10698938B2 (en) 2016-03-18 2020-06-30 Palantir Technologies Inc. Systems and methods for organizing and identifying documents via hierarchies and dimensions of tags
CN107230008B (en) * 2016-03-25 2020-03-27 阿里巴巴集团控股有限公司 Risk information output and risk information construction method and device
US10872339B1 (en) 2016-03-25 2020-12-22 State Farm Mutual Automobile Insurance Company Reducing false positives using customer feedback and machine learning
US10210518B2 (en) * 2016-04-13 2019-02-19 Abdullah Abdulaziz I. Alnajem Risk-link authentication for optimizing decisions of multi-factor authentications
US10776876B1 (en) 2016-04-13 2020-09-15 Wells Fargo Bank, N.A. Virtual wallet insurance
US20210357771A1 (en) 2016-05-12 2021-11-18 State Farm Mutual Automobile Insurance Company Natural language virtual assistant
US11544783B1 (en) 2016-05-12 2023-01-03 State Farm Mutual Automobile Insurance Company Heuristic credit risk assessment engine
US10783535B2 (en) 2016-05-16 2020-09-22 Cerebri AI Inc. Business artificial intelligence management engine
US10356028B2 (en) * 2016-05-25 2019-07-16 Alphabet Communications, Inc. Methods, systems, and devices for generating a unique electronic communications account based on a physical address and applications thereof
CN107563757B (en) * 2016-07-01 2020-09-22 阿里巴巴集团控股有限公司 Data risk identification method and device
US10719188B2 (en) 2016-07-21 2020-07-21 Palantir Technologies Inc. Cached database and synchronization system for providing dynamic linked panels in user interface
US10324609B2 (en) 2016-07-21 2019-06-18 Palantir Technologies Inc. System for providing dynamic linked panels in user interface
US10437840B1 (en) 2016-08-19 2019-10-08 Palantir Technologies Inc. Focused probabilistic entity resolution from multiple data sources
US11151566B2 (en) * 2016-09-19 2021-10-19 Early Warning Services, Llc Authentication and fraud prevention in provisioning a mobile wallet
WO2018074902A2 (en) * 2016-10-20 2018-04-26 Samsung Electronics Co., Ltd. System and method for mobile wallet remittance
US10318630B1 (en) 2016-11-21 2019-06-11 Palantir Technologies Inc. Analysis of large bodies of textual data
US10620618B2 (en) 2016-12-20 2020-04-14 Palantir Technologies Inc. Systems and methods for determining relationships between defects
US11238528B2 (en) * 2016-12-22 2022-02-01 American Express Travel Related Services Company, Inc. Systems and methods for custom ranking objectives for machine learning models applicable to fraud and credit risk assessments
US10460602B1 (en) 2016-12-28 2019-10-29 Palantir Technologies Inc. Interactive vehicle information mapping system
CN108346048B (en) 2017-01-23 2020-07-28 阿里巴巴集团控股有限公司 Method for adjusting risk parameters, risk identification method and risk identification device
US10762563B2 (en) * 2017-03-10 2020-09-01 Cerebri AI Inc. Monitoring and controlling continuous stochastic processes based on events in time series data
FR3064095B1 (en) * 2017-03-16 2019-06-14 Worldline AUTOMATIC LEARNING DETECTION OF ANOMALIES IN A SET OF BANKING TRANSACTIONS BY OPTIMIZING THE AVERAGE PRECISION
US10325224B1 (en) 2017-03-23 2019-06-18 Palantir Technologies Inc. Systems and methods for selecting machine learning training data
US10313344B2 (en) 2017-03-30 2019-06-04 Bank Of America Corporation Internal footprint repository
US10606866B1 (en) 2017-03-30 2020-03-31 Palantir Technologies Inc. Framework for exposing network activities
US10235461B2 (en) 2017-05-02 2019-03-19 Palantir Technologies Inc. Automated assistance for generating relevant and valuable search results for an entity of interest
US10482382B2 (en) 2017-05-09 2019-11-19 Palantir Technologies Inc. Systems and methods for reducing manufacturing failure rates
US20180350006A1 (en) * 2017-06-02 2018-12-06 Visa International Service Association System, Method, and Apparatus for Self-Adaptive Scoring to Detect Misuse or Abuse of Commercial Cards
US10956406B2 (en) 2017-06-12 2021-03-23 Palantir Technologies Inc. Propagated deletion of database records and derived data
CN107423883B (en) * 2017-06-15 2020-04-07 创新先进技术有限公司 Risk identification method and device for to-be-processed service and electronic equipment
US10403011B1 (en) 2017-07-18 2019-09-03 Palantir Technologies Inc. Passing system with an interactive user interface
US20190026742A1 (en) * 2017-07-20 2019-01-24 Microsoft Technology Licensing, Llc Accounting for uncertainty when calculating profit efficiency
US10078839B1 (en) * 2017-08-30 2018-09-18 Square, Inc. Centralized system for data retrieval
US11537867B2 (en) 2017-09-27 2022-12-27 Visa International Service Association System and method for online analysis
US10699028B1 (en) 2017-09-28 2020-06-30 Csidentity Corporation Identity security architecture systems and methods
US20200327549A1 (en) * 2017-11-08 2020-10-15 Paypal, Inc. Robust and Adaptive Artificial Intelligence Modeling
US10896472B1 (en) 2017-11-14 2021-01-19 Csidentity Corporation Security and identity verification system and architecture
US10776789B2 (en) 2017-11-15 2020-09-15 Mastercard International Incorporated Data analysis systems and methods for identifying recurring payment programs
US11410062B2 (en) * 2017-12-19 2022-08-09 Yahoo Ad Tech Llc Method and system for reducing risk values discrepancies between categories
US11461841B2 (en) 2018-01-03 2022-10-04 QCash Financial, LLC Statistical risk management system for lending decisions
US11205222B2 (en) * 2018-01-03 2021-12-21 QCash Financial, LLC Centralized model for lending risk management system
CN108399543B (en) 2018-01-23 2020-09-04 阿里巴巴集团控股有限公司 Binding method and trust evaluation method and device of payment card and electronic equipment
WO2019172887A1 (en) * 2018-03-06 2019-09-12 Visa International Service Association Automated decision analysis by model operational characteristic curves
WO2019173554A1 (en) * 2018-03-07 2019-09-12 Coral Protocol Blockchain transaction safety
US11599369B1 (en) 2018-03-08 2023-03-07 Palantir Technologies Inc. Graphical user interface configuration system
US11455641B1 (en) * 2018-03-11 2022-09-27 Secureauth Corporation System and method to identify user and device behavior abnormalities to continuously measure transaction risk
CN110309840B (en) 2018-03-27 2023-08-11 创新先进技术有限公司 Risk transaction identification method, risk transaction identification device, server and storage medium
US10754822B1 (en) 2018-04-18 2020-08-25 Palantir Technologies Inc. Systems and methods for ontology migration
US10648889B2 (en) 2018-04-30 2020-05-12 Nxp B.V. Monitor system for detecting defeat devices in engine control units
US20190342297A1 (en) 2018-05-01 2019-11-07 Brighterion, Inc. Securing internet-of-things with smart-agent technology
US10885021B1 (en) 2018-05-02 2021-01-05 Palantir Technologies Inc. Interactive interpreter and graphical user interface
US11538128B2 (en) 2018-05-14 2022-12-27 Verint Americas Inc. User interface for fraud alert management
CN108629137B (en) * 2018-05-14 2021-12-24 苏州科技大学 Optimization design method for structural parameters of mechanical structural part
US11119630B1 (en) 2018-06-19 2021-09-14 Palantir Technologies Inc. Artificial intelligence assisted evaluations and user interface for same
CN109191226B (en) * 2018-06-29 2021-10-12 创新先进技术有限公司 Risk control method and device
US20200027158A1 (en) * 2018-07-17 2020-01-23 Credit One Bank, N.A. Distributed consumer authentication and credit offer location
US20210192527A1 (en) * 2018-08-30 2021-06-24 Yue Li Artificial intelligence enhanced transaction suspension
US11100508B2 (en) 2018-09-06 2021-08-24 Mastercard International Incorporated Multi-party payment card processing systems and methods with foreign exchange transaction detection and chargeback loss mitigation
KR20200034020A (en) 2018-09-12 2020-03-31 삼성전자주식회사 Electronic apparatus and control method thereof
TWI709188B (en) 2018-09-27 2020-11-01 財團法人工業技術研究院 Fusion-based classifier, classification method, and classification system
US11068942B2 (en) 2018-10-19 2021-07-20 Cerebri AI Inc. Customer journey management engine
US10887452B2 (en) 2018-10-25 2021-01-05 Verint Americas Inc. System architecture for fraud detection
US11102092B2 (en) * 2018-11-26 2021-08-24 Bank Of America Corporation Pattern-based examination and detection of malfeasance through dynamic graph network flow analysis
US11276064B2 (en) 2018-11-26 2022-03-15 Bank Of America Corporation Active malfeasance examination and detection based on dynamic graph network flow analysis
US10769636B2 (en) 2018-11-29 2020-09-08 International Business Machines Corporation Cognitive fraud detection through variance-based network analysis
US11050772B2 (en) 2018-12-05 2021-06-29 Bank Of America Corporation Method and system for identification and prevention of profiling attacks in electronic authorization systems
CN109816390A (en) * 2019-01-03 2019-05-28 深圳壹账通智能科技有限公司 Anti- fraud analysis processing method, device and computer equipment based on transaction data
JP7152331B2 (en) 2019-02-15 2022-10-12 敏弘 吉▲崎▼ ordering system
WO2020189522A1 (en) * 2019-03-19 2020-09-24 日本電気株式会社 Score distribution conversion device, score distribution conversion method, and score distribution conversion program
US11748757B1 (en) * 2019-04-19 2023-09-05 Mastercard International Incorporated Network security systems and methods for detecting fraud
US11741465B2 (en) 2019-05-02 2023-08-29 Mastercard International Incorporated Systems and methods for generating pre-chargeback dispute records
US11107084B2 (en) * 2019-05-03 2021-08-31 Walmart Apollo, Llc Fraud risk scoring tool
US11449611B2 (en) 2019-05-21 2022-09-20 Nxp B.V. Apparatuses and methods involving a circuit for detecting a hardware-trojan
IL303147A (en) 2019-06-20 2023-07-01 Verint Americas Inc Systems and methods for authentication and fraud detection
JP6743319B1 (en) * 2019-06-26 2020-08-19 楽天株式会社 Fraud estimation system, fraud estimation method, and program
US11403641B2 (en) 2019-06-28 2022-08-02 Paypal, Inc. Transactional probability analysis on radial time representation
CN110503563B (en) * 2019-07-05 2023-07-21 中国平安人寿保险股份有限公司 Risk control method and system
US20210073803A1 (en) * 2019-09-05 2021-03-11 SOURCE Ltd. System and method for validating monetary transactions
US20210097543A1 (en) * 2019-09-30 2021-04-01 Microsoft Technology Licensing, Llc Determining fraud risk indicators using different fraud risk models for different data phases
US20210110343A1 (en) * 2019-10-10 2021-04-15 United States Postal Service Methods and systems for generating address score information
CN110751493B (en) * 2019-10-11 2022-05-31 支付宝(杭州)信息技术有限公司 Risk prevention and control method and device based on historical reservation orders
US11868453B2 (en) 2019-11-07 2024-01-09 Verint Americas Inc. Systems and methods for customer authentication based on audio-of-interest
CN110995688B (en) * 2019-11-27 2021-11-16 深圳申朴信息技术有限公司 Personal data sharing method and device for internet financial platform and terminal equipment
WO2020098825A2 (en) 2019-12-20 2020-05-22 Alipay (Hangzhou) Information Technology Co., Ltd. System and method for evaluating risk
US11308561B2 (en) * 2019-12-20 2022-04-19 Hartford Fire Insurance Company System and method using third-party data to provide risk relationship adjustment recommendation based on upcoming life event
US20220327186A1 (en) * 2019-12-26 2022-10-13 Rakuten Group, Inc. Fraud detection system, fraud detection method, and program
CN111177513B (en) * 2019-12-31 2023-10-31 北京百度网讯科技有限公司 Determination method and device of abnormal access address, electronic equipment and storage medium
US10778706B1 (en) 2020-01-10 2020-09-15 Capital One Services, Llc Fraud detection using graph databases
US20210241279A1 (en) * 2020-02-05 2021-08-05 International Business Machines Corporation Automatic fraud detection
EP3889871A1 (en) * 2020-04-01 2021-10-06 Worldline Drive for predictive models for automatic fraud detection from learning assemblies built in separate contexts.
EP4176392A4 (en) * 2020-07-01 2023-12-27 Visa International Service Association Residual neural networks for anomaly detection
US20220164699A1 (en) * 2020-11-25 2022-05-26 Paypal, Inc. Training and Using a Machine Learning Model to Make Predictions
US20220172211A1 (en) * 2020-11-30 2022-06-02 International Business Machines Corporation Applying machine learning to learn relationship weightage in risk networks
CN112954379B (en) * 2021-02-09 2023-04-21 中国工商银行股份有限公司 Live broadcast control method and device
US20220374903A1 (en) * 2021-05-19 2022-11-24 Paypal, Inc. Proximity-based token issuance system
US20220417265A1 (en) * 2021-06-29 2022-12-29 Microsoft Technology Licensing, Llc Anomaly detection in an application with delegate authorization
CN114625747B (en) * 2022-05-13 2022-08-12 杭银消费金融股份有限公司 Wind control updating method and system based on information security

Family Cites Families (169)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
USRE30580E (en) 1961-04-12 1981-04-14 Telecredit, Inc. Check authorization system
US3657702A (en) 1970-08-19 1972-04-18 Digital Data Systems Corp Transaction accumulator for a credit verification system
US3950733A (en) 1974-06-06 1976-04-13 Nestor Associates Information processing system
US4044243A (en) 1976-07-23 1977-08-23 Nestor Associates Information processing system
USRE30579E (en) 1977-10-28 1981-04-14 Telecredit, Inc. Check authorization system
CA1172366A (en) * 1978-04-04 1984-08-07 Harold W. Gosling Methods and apparatus for encoding and constructing signals
US4388582A (en) * 1978-05-31 1983-06-14 Black & Decker Inc. Apparatus and method for charging batteries
US4254474A (en) 1979-08-02 1981-03-03 Nestor Associates Information processing system using threshold passive modification
US4305059A (en) 1980-01-03 1981-12-08 Benton William M Modular funds transfer system
US4326259A (en) 1980-03-27 1982-04-20 Nestor Associates Self organizing general pattern class separator and identifier
US4578530A (en) 1981-06-26 1986-03-25 Visa U.S.A., Inc. End-to-end encryption system and method of operation
US4674058A (en) * 1981-12-07 1987-06-16 Dicomed Corporation Method and apparatus for flexigon representation of a two dimensional figure
US4486836A (en) * 1981-12-22 1984-12-04 Schlumberger Technology Corporation Well logging: utilizing superposition of step-profile responses of logging tools to improve logs
US4485300A (en) 1982-03-18 1984-11-27 Visa U.S.A., Inc. Loss control system
DE3223034C2 (en) 1982-06-19 1986-12-11 Mico Datensysteme GmbH, 7252 Weil der Stadt Procedure for the detection of counterfeit data carriers
JPH0642244B2 (en) 1982-07-09 1994-06-01 オムロン株式会社 Margin transaction processing device
US4528643A (en) 1983-01-10 1985-07-09 Fpdc, Inc. System for reproducing information in material objects at a point of sale location
GB2146814A (en) 1983-09-17 1985-04-24 Ibm Electronic fund transfer systems
US4734858B1 (en) 1983-12-05 1997-02-11 Portel Services Network Inc Data terminal and system for placing orders
US4760604A (en) 1985-02-15 1988-07-26 Nestor, Inc. Parallel, multi-unit, adaptive, nonlinear pattern class separator and identifier
US4812628A (en) 1985-05-02 1989-03-14 Visa International Service Association Transaction system with off-line risk assessment
US4734564A (en) 1985-05-02 1988-03-29 Visa International Service Association Transaction system with off-line risk assessment
US4792968A (en) 1985-07-10 1988-12-20 Fdr Interactive Technologies Statistical analysis system for use with public communication facility
US4845739A (en) 1985-07-10 1989-07-04 Fdr Interactive Technologies Telephonic-interface statistical analysis system
US4755935A (en) 1986-01-27 1988-07-05 Schlumberger Technology Corporation Prefetch memory system having next-instruction buffer which stores target tracks of jumps prior to CPU access of instruction
US4785391A (en) * 1986-02-07 1988-11-15 Bitstream Inc. Automated bitmap character generation from outlines
JPH0778165B2 (en) 1986-06-27 1995-08-23 東芝ケミカル株式会社 Heat-resistant resin composition for molding
NL8602245A (en) 1986-09-05 1988-04-05 Philips Nv SYSTEM FOR PROVIDING A TELECOMMUNICATIONS CONNECTION TO A COMPUTER.
US4799156A (en) 1986-10-01 1989-01-17 Strategic Processing Corporation Interactive market management system
US4827508A (en) 1986-10-14 1989-05-02 Personal Library Software, Inc. Database usage metering and protection system and method
US4935870A (en) 1986-12-15 1990-06-19 Keycom Electronic Publishing Apparatus for downloading macro programs and executing a downloaded macro program responding to activation of a single key
US4795890A (en) 1987-02-02 1989-01-03 Light Signatures, Inc. Device authentication system for on and off line use
US4949257A (en) 1987-04-28 1990-08-14 Zvi Orbach Automated merchandising system for computer software
US4897811A (en) 1988-01-19 1990-01-30 Nestor, Inc. N-dimensional coulomb neural network which provides for cumulative learning of internal representations
US4958375A (en) 1988-02-17 1990-09-18 Nestor, Inc. Parallel, multi-unit, adaptive pattern classification system using inter-unit correlations and an intra-unit class separator methodology
JPH01255993A (en) 1988-04-05 1989-10-12 Sharp Corp Cash register
US5025373A (en) 1988-06-30 1991-06-18 Jml Communications, Inc. Portable personal-banking system
CA1337132C (en) 1988-07-15 1995-09-26 Robert Filepp Reception system for an interactive computer network and method of operation
US4947028A (en) 1988-07-19 1990-08-07 Arbor International, Inc. Automated order and payment system
US5247575A (en) 1988-08-16 1993-09-21 Sprague Peter J Information distribution system
US4982346A (en) 1988-12-16 1991-01-01 Expertel Communications Incorporated Mall promotion network apparatus and method
US5255342A (en) * 1988-12-20 1993-10-19 Kabushiki Kaisha Toshiba Pattern recognition system and method using neural network
US5077607A (en) 1988-12-23 1991-12-31 Scientific-Atlanta, Inc. Cable television transaction terminal
US4992940A (en) 1989-03-13 1991-02-12 H-Renee, Incorporated System and method for automated selection of equipment for purchase through input of user desired specifications
US4977595A (en) 1989-04-03 1990-12-11 Nippon Telegraph And Telephone Corporation Method and apparatus for implementing electronic cash
US4893330A (en) 1989-06-01 1990-01-09 American Telephone And Telegraph Company, At&T Bell Laboratories Method and apparatus for restricting credit card communication calls
US5206488A (en) 1989-06-07 1993-04-27 Mordechai Teicher Credit card system including a central unit and a plurality of local units for conducting low-cost transactions
FR2651903B1 (en) * 1989-09-12 1991-12-06 Michaud Andre METHOD FOR LIMITING THE RISKS ATTACHED TO A COMPUTER TRANSACTION.
US5138695A (en) 1989-10-10 1992-08-11 Hnc, Inc. Systolic array image processing system
US5220501A (en) 1989-12-08 1993-06-15 Online Resources, Ltd. Method and system for remote delivery of retail banking services
US5623547A (en) 1990-04-12 1997-04-22 Jonhig Limited Value transfer system
GB2242976A (en) * 1990-04-12 1991-10-16 Rank Taylor Hobson Ltd Measuring surface characteristics
EP0468229A3 (en) * 1990-07-27 1994-01-26 Hnc Inc A neural network with expert system functionality
AU656542B2 (en) 1990-10-01 1995-02-09 Thomas A. Bush Transactional processing system
US5177342A (en) 1990-11-09 1993-01-05 Visa International Service Association Transaction approval system
US5231570A (en) 1990-12-11 1993-07-27 Lee Gerritt S K Credit verification system
US5175682A (en) 1990-12-14 1992-12-29 Verifone, Inc. Check system and method including prioritizing checks for transmission to banks for processing
US5291550A (en) 1990-12-26 1994-03-01 At&T Bell Laboratories Dynamic network call distributor
US5351186A (en) 1991-01-16 1994-09-27 Bullock Communications, Inc. System and method for obtaining information concerning a product or a service
US5253341A (en) 1991-03-04 1993-10-12 Rozmanith Anthony I Remote query communication system
US5383113A (en) 1991-07-25 1995-01-17 Checkfree Corporation System and method for electronically providing customer services including payment of bills, financial analysis and loans
EP0611513B1 (en) 1991-11-08 1998-09-23 Electronic Data Systems Corporation Apparatus for detecting and preventing subscriber number cloning in a cellular mobile telephone system
US5559895A (en) * 1991-11-08 1996-09-24 Cornell Research Foundation, Inc. Adaptive method and system for real time verification of dynamic human signatures
US5557518A (en) 1994-04-28 1996-09-17 Citibank, N.A. Trusted agents for open electronic commerce
US5305195A (en) 1992-03-25 1994-04-19 Gerald Singer Interactive advertising system for on-line terminals
AU4237293A (en) 1992-05-08 1993-12-13 Release Management Systems (Rms) Data interchange system
US5336870A (en) 1992-05-26 1994-08-09 Hughes Thomas S System for remote purchase payment transactions and remote bill payments
US7251624B1 (en) * 1992-09-08 2007-07-31 Fair Isaac Corporation Score based decisioning
US5819226A (en) 1992-09-08 1998-10-06 Hnc Software Inc. Fraud detection using predictive modeling
EP0598469A3 (en) 1992-10-27 1996-07-10 Daniel P Dunlevy Interactive credit card fraud control process.
US5377269A (en) 1992-10-29 1994-12-27 Intelligent Security Systems, Inc. Security access and monitoring system for personal computer
JPH06149849A (en) 1992-11-05 1994-05-31 Kanegafuchi Chem Ind Co Ltd Product shipment amount estimating device
US5341429A (en) 1992-12-04 1994-08-23 Testdrive Corporation Transformation of ephemeral material
US5351293A (en) 1993-02-01 1994-09-27 Wave Systems Corp. System method and apparatus for authenticating an encrypted signal
US5321751A (en) 1993-02-18 1994-06-14 Eastman Kodak Company Method and apparatus for credit card verification
US5420405A (en) 1993-02-26 1995-05-30 Chasek; Norman E. Secure, automated transaction system that supports an electronic currency operating in mixed debit & credit modes
US5311594A (en) 1993-03-26 1994-05-10 At&T Bell Laboratories Fraud protection for card transactions
US5351296A (en) 1993-03-29 1994-09-27 Niobrara Research & Development Corporation Financial transmission system
US5479574A (en) 1993-04-01 1995-12-26 Nestor, Inc. Method and apparatus for adaptive classification
US5491817A (en) 1993-05-25 1996-02-13 Bell Communications Research Inc. Linking system and method for accessing directory information about an object in one context when information in another context is known
US5414833A (en) 1993-10-27 1995-05-09 International Business Machines Corporation Network security system and method using a parallel finite state machine adaptive active monitor and responder
GB2283349A (en) 1993-10-29 1995-05-03 Ibm Transaction processing system
GB9323489D0 (en) 1993-11-08 1994-01-05 Ncr Int Inc Self-service business system
DE69431306T2 (en) 1993-12-16 2003-05-15 Open Market Inc NETWORK-BASED PAYMENT SYSTEM AND METHOD FOR USING SUCH A SYSTEM
US5542054A (en) * 1993-12-22 1996-07-30 Batten, Jr.; George W. Artificial neurons using delta-sigma modulation
US5704018A (en) * 1994-05-09 1997-12-30 Microsoft Corporation Generating improved belief networks
US5500513A (en) 1994-05-11 1996-03-19 Visa International Automated purchasing control system
US5528701A (en) * 1994-09-02 1996-06-18 Panasonic Technologies, Inc. Trie based method for indexing handwritten databases
US5511122A (en) 1994-06-03 1996-04-23 The United States Of America As Represented By The Secretary Of The Navy Intermediate network authentication
US5701398A (en) 1994-07-01 1997-12-23 Nestor, Inc. Adaptive classifier having multiple subnetworks
US5940529A (en) * 1994-07-25 1999-08-17 Buckley; B. Shawn Self-organizing circuits
US5515307A (en) 1994-08-04 1996-05-07 Bell Communications Research, Inc. Pseudo-random generator
US6025128A (en) * 1994-09-29 2000-02-15 The University Of Tulsa Prediction of prostate cancer progression by analysis of selected predictive parameters
US5596642A (en) 1994-09-30 1997-01-21 Electronic Payment Services, Inc. Network settlement performed on consolidated information
US5715314A (en) 1994-10-24 1998-02-03 Open Market, Inc. Network sales system
US5732400A (en) 1995-01-04 1998-03-24 Citibank N.A. System and method for a risk-based purchase of goods
US5530438A (en) 1995-01-09 1996-06-25 Motorola, Inc. Method of providing an alert of a financial transaction
US5696909A (en) 1995-01-27 1997-12-09 Hypercom, Inc. Virtual POS terminal
DE69637799D1 (en) 1995-02-13 2009-02-12 Intertrust Tech Corp Systems and procedures for secure transaction management and electronic legal protection
US5696907A (en) * 1995-02-27 1997-12-09 General Electric Company System and method for performing risk and credit analysis of financial service applications
US5826245A (en) 1995-03-20 1998-10-20 Sandberg-Diment; Erik Providing verification information for a transaction
US5553145A (en) 1995-03-21 1996-09-03 Micali; Silvia Simultaneous electronic transactions with visible trusted parties
US5590197A (en) 1995-04-04 1996-12-31 V-One Corporation Electronic payment system and method
US5708422A (en) 1995-05-31 1998-01-13 At&T Transaction authorization and alert system
US5680511A (en) 1995-06-07 1997-10-21 Dragon Systems, Inc. Systems and methods for word recognition
AU6279896A (en) * 1995-06-15 1997-01-15 Fraudetect, L.L.C. Process and apparatus for detecting fraud
US5884289A (en) 1995-06-16 1999-03-16 Card Alert Services, Inc. Debit card fraud detection and control system
US5802497A (en) 1995-07-10 1998-09-01 Digital Equipment Corporation Method and apparatus for conducting computerized commerce
US5809144A (en) 1995-08-24 1998-09-15 Carnegie Mellon University Method and apparatus for purchasing and delivering digital goods over a network
US5710887A (en) 1995-08-29 1998-01-20 Broadvision Computer system and method for electronic commerce
US5671280A (en) 1995-08-30 1997-09-23 Citibank, N.A. System and method for commercial payments using trusted agents
US5757917A (en) 1995-11-01 1998-05-26 First Virtual Holdings Incorporated Computerized payment system for purchasing goods and services on the internet
US5758327A (en) 1995-11-01 1998-05-26 Ben D. Gardner Electronic requisition and authorization process
US5608801A (en) 1995-11-16 1997-03-04 Bell Communications Research, Inc. Efficient cryptographic hash functions and methods for amplifying the security of hash functions and pseudo-random functions
US5875236A (en) 1995-11-21 1999-02-23 At&T Corp Call handling method for credit and fraud management
US5870473A (en) 1995-12-14 1999-02-09 Cybercash, Inc. Electronic transfer system and method
US5805686A (en) 1995-12-22 1998-09-08 Mci Corporation Telephone fraud detection system
US5822737A (en) 1996-02-05 1998-10-13 Ogram; Mark E. Financial transaction system
US5745654A (en) 1996-02-13 1998-04-28 Hnc Software, Inc. Fast explanations of scored observations
US5850442A (en) 1996-03-26 1998-12-15 Entegrity Solutions Corporation Secure world wide electronic commerce over an open network
US5905736A (en) 1996-04-22 1999-05-18 At&T Corp Method for the billing of transactions over the internet
US5815657A (en) 1996-04-26 1998-09-29 Verifone, Inc. System, method and article of manufacture for network electronic authorization utilizing an authorization instrument
US5988497A (en) 1996-05-30 1999-11-23 Mci Communications Corporation Method for authenticating credit transactions to prevent fraudulent charges
US5729594A (en) 1996-06-07 1998-03-17 Klingman; Edwin E. On-line secured financial transaction system through electronic media
US6094643A (en) 1996-06-14 2000-07-25 Card Alert Services, Inc. System for detecting counterfeit financial card fraud
US5897621A (en) 1996-06-14 1999-04-27 Cybercash, Inc. System and method for multi-currency transactions
US5812668A (en) 1996-06-17 1998-09-22 Verifone, Inc. System, method and article of manufacture for verifying the operation of a remote transaction clearance system utilizing a multichannel, extensible, flexible architecture
US5790645A (en) 1996-08-01 1998-08-04 Nynex Science & Technology, Inc. Automatic design of fraud detection systems
US5903830A (en) 1996-08-08 1999-05-11 Joao; Raymond Anthony Transaction security apparatus and method
US5953710A (en) * 1996-10-09 1999-09-14 Fleming; Stephen S. Children's credit or debit card system
US5832465A (en) * 1997-04-07 1998-11-03 General Electric Company Method for building a self-learning evidential reasoning system
US6119103A (en) * 1997-05-27 2000-09-12 Visa International Service Association Financial risk prediction systems and methods therefor
US6000608A (en) 1997-07-10 1999-12-14 Dorf; Robert E. Multifunction card system
US7403922B1 (en) * 1997-07-28 2008-07-22 Cybersource Corporation Method and apparatus for evaluating fraud risk in an electronic commerce transaction
US6029154A (en) * 1997-07-28 2000-02-22 Internet Commerce Services Corporation Method and system for detecting fraud in a credit card transaction over the internet
US5899980A (en) 1997-08-11 1999-05-04 Trivnet Ltd. Retail method over a wide area network
US6807537B1 (en) * 1997-12-04 2004-10-19 Microsoft Corporation Mixtures of Bayesian networks
US6212504B1 (en) * 1998-01-12 2001-04-03 Unisys Corporation Self-authentication of value documents using encoded indices
JPH11259571A (en) 1998-03-13 1999-09-24 Nippon Telegr & Teleph Corp <Ntt> Electronic business transaction system unauthorized utilization detection method and device
US6078904A (en) * 1998-03-16 2000-06-20 Saddle Peak Systems Risk direct asset allocation and risk resolved CAPM for optimally allocating investment assets in an investment portfolio
US6163604A (en) 1998-04-03 2000-12-19 Lucent Technologies Automated fraud management in transaction-based networks
JPH11328318A (en) 1998-05-11 1999-11-30 Sharp Corp Probability table generating device, probability system language processor, recognizing device, and record medium
US20030014379A1 (en) * 1999-07-01 2003-01-16 Isaac Saias Adaptive and reliable system and method for operations management
US6182070B1 (en) * 1998-08-21 2001-01-30 International Business Machines Corporation System and method for discovering predictive association rules
US6189005B1 (en) * 1998-08-21 2001-02-13 International Business Machines Corporation System and method for mining surprising temporal patterns
JP4218099B2 (en) 1998-12-03 2009-02-04 ソニー株式会社 Database, customer information search method, and customer information search device
US6278997B1 (en) * 1999-02-05 2001-08-21 International Business Machines Corporation System and method for constraint-based rule mining in large, dense data-sets
US6430539B1 (en) 1999-05-06 2002-08-06 Hnc Software Predictive modeling of consumer financial behavior
US6536037B1 (en) * 1999-05-27 2003-03-18 Accenture Llp Identification of redundancies and omissions among components of a web based architecture
US6609118B1 (en) * 1999-06-21 2003-08-19 General Electric Company Methods and systems for automated property valuation
DE59912157D1 (en) * 1999-09-02 2005-07-14 Gzs Ges Fuer Zahlungssysteme M expert system
US20030097292A1 (en) * 1999-09-30 2003-05-22 Christopher L Bernard System and method for stability analysis of profitability of target markets for goods or services
JP2001109733A (en) 1999-10-12 2001-04-20 Hitachi Ltd Method for evaluating identification model and method for adjusting threshold
US6418436B1 (en) * 1999-12-20 2002-07-09 First Data Corporation Scoring methodology for purchasing card fraud detection
US7167844B1 (en) * 1999-12-22 2007-01-23 Accenture Llp Electronic menu document creator in a virtual financial environment
US7069234B1 (en) * 1999-12-22 2006-06-27 Accenture Llp Initiating an agreement in an e-commerce environment
US6629081B1 (en) * 1999-12-22 2003-09-30 Accenture Llp Account settlement and financing in an e-commerce environment
US7418417B2 (en) * 2000-02-11 2008-08-26 Goldman Sachs & Co. Credit index, a system and method for structuring a credit index, and a system and method for operating a credit index
AU2001241609A1 (en) 2000-02-23 2001-09-03 Capital One Financial Corporation Systems and methods for providing anonymous financial transactions
KR20020086695A (en) * 2000-03-24 2002-11-18 알티코 인크. System and method for detecting fraudulent transactions
IL152502A0 (en) * 2000-04-28 2003-05-29 Internet Security Systems Inc Method and system for managing computer security information
US7376618B1 (en) * 2000-06-30 2008-05-20 Fair Isaac Corporation Detecting and measuring risk with predictive models using content mining
AU2001279026B2 (en) * 2000-07-25 2005-12-22 Angiodynamics, Inc. Apparatus for detecting and treating tumors using localized impedance measurement
US20020128960A1 (en) * 2000-12-29 2002-09-12 Lambiotte Kenneth G. Systems and methods for managing accounts
US7356503B1 (en) * 2001-02-21 2008-04-08 Fair Isaac And Company, Inc. ASP business decision engine
US7590594B2 (en) * 2001-04-30 2009-09-15 Goldman Sachs & Co. Method, software program, and system for ranking relative risk of a plurality of transactions
WO2002099598A2 (en) * 2001-06-07 2002-12-12 First Usa Bank, N.A. System and method for rapid updating of credit information
US7356506B2 (en) * 2002-09-18 2008-04-08 General Electric Capital Corporation Methods and apparatus for evaluating a credit application
US20040064401A1 (en) * 2002-09-27 2004-04-01 Capital One Financial Corporation Systems and methods for detecting fraudulent information

Also Published As

Publication number Publication date
AU2002311941A1 (en) 2002-12-09
EP1390833A4 (en) 2006-06-14
US7865427B2 (en) 2011-01-04
US8019678B2 (en) 2011-09-13
WO2002097563A2 (en) 2002-12-05
WO2002097563A3 (en) 2003-03-27
EP1390833A2 (en) 2004-02-25
US20110047044A1 (en) 2011-02-24
US20110282778A1 (en) 2011-11-17
JP2004537781A (en) 2004-12-16
US20020194119A1 (en) 2002-12-19

Similar Documents

Publication Publication Date Title
US7865427B2 (en) Method and apparatus for evaluating fraud risk in an electronic commerce transaction
US7403922B1 (en) Method and apparatus for evaluating fraud risk in an electronic commerce transaction
JP5265213B2 (en) Method and apparatus for assessing fraud risk in electronic commerce
Quah et al. Real-time credit card fraud detection using computational intelligence
US10580005B2 (en) Method and system for providing risk information in connection with transaction processing
US8429070B2 (en) Real time adaptive control of transaction review rate score curve
AU2012230299B2 (en) An automated fraud detection method and system
US20230274009A1 (en) System for designing and validating fine grained fraud detection rules
US20100057622A1 (en) Distributed Quantum Encrypted Pattern Generation And Scoring
US20120109802A1 (en) Verifying identity through use of an integrated risk assessment and management system
US20220261795A1 (en) Enhanced Feedback Exposure for Users Based on Transaction Metadata
US20230169553A1 (en) Determining an automatic acquisition approach for an exchange item request
US11869006B1 (en) Systems and methods for identifying synthetic party identities associated with network communications
US20220261802A1 (en) Dynamic Transmission Metadata Validation Adjustment Based on Network Conditions
Baloch et al. Application of Neural Network in Fraud Detection Using Business Concepts

Legal Events

Date Code Title Description
EEER Examination request
FZDE Discontinued

Effective date: 20150519