RISK ASSESSMENT RULE SET APPLICATION FOR FRAUD PREVENTION

• US 20100287099A1
• Filed: 05/05/2010
• Published: 11/11/2010
• Est. Priority Date: 05/07/2009
• Status: Active Grant

• Current Assignee: Visa USA, Inc. (Visa, Inc.)
• Original Assignee: Visa USA, Inc. (Visa, Inc.)
• Inventors: Brown, Christopher, Dwyer, Thomas, Liu, Frederick, Siegel, Kevin, Hilgers, Nancy, Nelsen, Mark
• Granted Patent: US 8,924,279 B2
• Time in Patent Office: Days
• US Class Current: 705/44
• CPC Class Codes: G06Q 20/40 Authorisation, 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
• CPC Class Codes: G06Q 20/4016 involving fraud or risk level assessment in transaction processing
• CPC Class Codes: G06Q 20/405 Establishing or using transaction specific rules

Abstract

Rules, applied to deny authorization of likely fraudulent transactions, are derived from a modified Patient Rule Induction Method algorithm that uses a target variable and a data set of past transactions each associated with a plurality of input variables and a hyper-rectangle enclosing a multi-dimensional space defined by a representation of the input variable values as points within the multi-dimensional space. While a count of the points within the hyper-rectangle is greater than a minimum support parameter, a first plurality of points proximal to edges of the hyper-rectangle are removed, where each such removing maximizes a mean value of the target variable, and then, while the mean value remains maximized, a second plurality of points proximal to the edges is added, where each adding maximizes or maintains the mean value. The hyper-rectangle is bounded within a minimum bounding box that defines the rules.

Claims

1. Any method, performed by hardware executing software, of determining whether to authorize a transaction using transaction authorization business rules identified from a minimum bounding box derived from a modified Patient Rule Induction Method (PRIM) algorithm, wherein the transaction is being conducted with a merchant on an account issued by an issuer to an account holder and the merchant submits information for the transaction to an acquirer for submission to an entity for the determination of whether to authorize the transaction using the transaction authorization business rules.

2. The method as defined in claim 1, wherein the modified Patient Rule Induction Method (PRIM) algorithm operates on a data set of past said transactions that were conducted in a payment processing system, wherein each said transaction was conducted on one said account issued by one said issuer to one said account holder and the one said account holder conducted the transaction with one said merchant for submission to the one said merchant'"'"'s acquirer.

3. The method as defined in claim 2, wherein the modified PRIM algorithm comprises the steps of:

defining a hyper-rectangle enclosing a multi-dimensional space defined by a plurality of input variable values, wherein;

the input variable values respectively correspond to input variables that are represented as points within the multi-dimensional space;

the hyper-rectangle has a plurality of edges each of which is associated with one of the plurality of input variables; and

the plurality of input variables, each having one said input variable value, are associated with the data set;

obtaining a target variable associated with the data set, wherein the target variable represents an output value based on at least one input variable value;

while a count of the points within the hyper-rectangle is greater than a minimum support parameter, removing a first plurality of points proximal to the plurality of edges of the hyper-rectangle, wherein each said removing maximizes a mean value of a target variable for the hyper-rectangle, wherein the target variable is associated with the data set and represents an output value based on at least one said input variable value;

while the mean value remains maximized, adding a second plurality of points proximal to the plurality of edges, wherein each said adding maximizes or maintains the mean value;

bounding the hyper-rectangle within the minimum bounding box; and

deriving, using the minimum bounding box, the transaction authorization business rules.

4. A non-transitory computer readable medium comprising instructions which, when executed by a computing apparatus, performs the method as defined in claim 1.

5. A method comprising a plurality of steps each being performed by computing apparatus executing software, wherein the steps include:

defining a hyper-rectangle enclosing a multi-dimensional space defined by a plurality of input variable values, wherein;

the input variable values respectively correspond to input variables that are represented as points within the multi-dimensional space;

the hyper-rectangle has a plurality of edges each of which is associated with one of the plurality of input variables;

the plurality of input variables, each having one said input variable value, are associated with a data set;

the data set corresponds to information from a plurality of transactions conducted in a payment processing system, wherein each said transaction is conducted on an account issued by an issuer to an account holder and the account holder conducts the transaction with a merchant for submission to the merchant'"'"'s acquirer for authorization thereof;

obtaining a target variable associated with the data set, wherein the target variable represents an output value based on at least one input variable value;

while a count of the points within the hyper-rectangle is greater than a minimum support parameter, removing a first plurality of points proximal to the plurality of edges, wherein each said removing maximizes a mean value of a target variable for the hyper-rectangle, wherein the target variable is associated with the data set and represents an output value based on at least one said input variable value;

while the mean value remains maximized, adding a second plurality of points proximal to the plurality of edges, wherein each said adding maximizes or maintains the mean value;

bounding the hyper-rectangle within a minimum bounding box; and

deriving, using the minimum bounding box, a plurality of business rules for use in determining whether to authorize a future said transaction between one said account holder and one said merchant.

6. The method as defined in claim 5, further comprising providing the plurality of business rules to either one of an issuer or a transaction handler.

7. The method as defined in claim 5, further comprising:

receiving an authorization request for the future said transaction between one said account holder and one said merchant, wherein the authorization request includes transaction data from the future said transaction;

determining whether there is a fraud hit by applying the plurality of business rules to the transaction data; and

operative if there is a fraud hit, sending an authorization response to the authorization request, wherein the authorization request includes information denying the future said transaction.

8. The method as defined in claim 7, further comprising operative if there is a fraud hit, notifying an issuer of an account upon which the denied transaction is being conducted.

9. The method as defined in claim 7, further comprising:

determining whether the future said transaction is eligible for Stand In Processing; and

operative if the future said transaction is eligible for Stand In Processing, applying a Stand In Processing procedure.

10. The method as defined in claim 9, further comprising operative if the future said transaction is not eligible for Stand In Processing, referring for processing the future said transaction to an issuer of an account upon which the future said transaction was being conducted.

11. The method as defined in claim 7, further comprising:

identifying, from the transaction data, at least one of an account number and a Bank Identification Number (BIN); and

determining whether the at least one of the account number and the BIN is a real-time decisioning participant, wherein when the at least one of the account number and the BIN is the real-time decisioning participant, the plurality of business rules are applied to the transaction data.

12. The method as defined in claim 7, wherein the fraud prevention rules are card-level real time decisioning rules, the method further comprising:

obtaining a card database;

identifying an account number from the transaction data; and

determining whether the account number is stored within the card database, wherein when the account number is stored within the card database the plurality of business rules are applied to the transaction data.

13. The method as defined in claim 7, wherein the fraud prevention rules are Bank Identification Numbers (BIN) level rules, the method further comprising:

obtaining a BIN database;

identifying a BIN from the transaction data; and

determining whether the BIN is stored within the BIN database, wherein when the BIN is store within the BIN database the plurality of business rules are applied to the transaction data.

14. The method as defined in claim 5, further comprising obtaining the minimum support parameter.

15. The method as defined in claim 5, further comprising obtaining a maximum peeling parameter, wherein the maximum peeling parameter is the maximum count of the first plurality of points that may be removed during each said removing.

16. The method as defined in claim 5, further comprising obtaining a condition associated with at least one input variable, wherein the multi-dimensional space is defined by input variable values that satisfy the condition.

17. A non-transitory computer readable medium comprising instructions which, when executed by a computing apparatus, performs The method as defined in claim 5.

18. In a payment processing system in which a transaction handler processes a plurality of transactions each characterized by a consumer and a merchant engaging in one said transaction upon an account within the payment processing system, wherein an issuer has issued the account to the consumer, and wherein the merchant submits the one said transaction to an acquirer for processing by the transaction handler who requests the issuer to disburse funds from the consumer for the one said transaction, and wherein the issuer forwards the funds to the transaction handler who forwards the funds to the acquirer to disburse the funds to the merchant for the one said transaction, a method comprising a plurality of steps each being performed by computing apparatus executing software, wherein the steps include:

defining a target variable associated with a data set, wherein the data set;

is associated with a plurality of input variables each having input variable values;

the target variable represents an output value based on at least one input variable value; and

corresponds to information from a plurality of said transactions conducted in the payment processing system, wherein each said transaction is conducted on one said account issued by on said issuer to one said account holder and the account holder conducts the transaction with one said merchant for submission to the merchant'"'"'s acquirer for authorization thereof;

providing the target variable to a business rules optimizer service for optimization, wherein said optimization comprises;

defining a hyper-rectangle enclosing a multi-dimensional space defined by the input variable values, wherein the input variable values are represented as points within the multi-dimensional space, wherein the hyper-rectangle has a plurality of edges, wherein each edge is associated with one of the plurality of input variables;

while a count of the points within the hyper-rectangle is greater than a minimum support parameter, removing a first plurality of points proximal to the plurality of edges, wherein each said removing maximizes a mean value of the target variable for the hyper-rectangle;

while the mean value remains maximized, adding a second plurality of points proximal to the plurality of edges, wherein each said adding maximizes or maintains the mean value;

bounding the hyper-rectangle within a minimum bounding box; and

identifying a plurality of transaction authorization business rules, defined by the minimum bounding box;

receiving the plurality of transaction authorization business rules from the optimizer service; and

providing the plurality of transaction authorization business rules to the transaction handler for use in determining whether to authorize a future said transaction between one said account holder and one said merchant.

19. The method as defined in claim 18, further comprising:

defining a minimum support parameter; and

providing the minimum support parameter to the business rules optimizer service.

20. The method as defined in claim 18, further comprising:

defining a maximum peeling parameter, wherein the maximum peeling parameter is the maximum count of the first plurality of points that may be removed during each said removing; and

providing the maximum peeling parameter to the business rules optimizer service.

21. The method as defined in claim 18, further comprising receiving notice from the transaction handler of a declined said transaction based upon the plurality of transaction authorization business rules.

22. The method as defined in claim 18, further comprising providing to the transaction handler a participant database identifying at least one of a plurality of account numbers and a plurality of Bank Identification Numbers (BIN), wherein the plurality of transaction authorization business rules are applied to respective said transactions associated with the at least one of the plurality of account numbers and the plurality of BIN numbers stored within the participant database.

23. The method as defined in claim 18, further comprising providing to the transaction handler an account database, wherein the plurality of transaction authorization business rules are:

card-level real time decisioning rules; and

applied to one said transaction associated with an account number stored within the account database.

24. The method as defined in claim 18, further comprising providing to the transaction handler a Bank Identification Number (BIN) database, wherein the plurality of transaction authorization business rules:

are BIN level rules; and

applied to one said transaction associated with a BIN stored within the BIN database.

25. The method as defined in claim 18, further comprising providing a condition associated with at least one input variable, wherein the multi-dimensional space is defined by input variable values that satisfy the condition.

26. The method as defined in claim 18, further comprising providing the data set to the business rules optimizer.

27. A non-transitory computer readable medium comprising instructions which, when executed by a computing apparatus, performs the method as defined in claim 18.