Iterative processing of transaction information to detect fraud

Abstract

A fraud management system is configured to store rules for detecting fraud, receive a transaction from a merchant, process the transaction using a first subset of rules to generate a fraud score for the transaction, and output information regarding the fraud score to the merchant to assist the merchant in determining whether to accept, deny, or fulfill the transaction. The fraud management system is further configured to receive, after outputting the information regarding the fraud score to the merchant, additional information relating to the transaction, re-process the transaction using a second subset of rules to generate an update fraud score, and output information regarding the updated fraud score to the merchant to assist the merchant in determining whether to accept, deny, or fulfill the transaction.

What is claimed is: 
     
         1 . A method, comprising:
 receiving, by one or more computer devices, first transaction data for a first transaction associated with a first consumer;   identifying, by the one or more computer devices, a plurality of first transaction attributes associated with the first transaction data;   determining, by the one or more computer devices and based on the first transaction data, a first fraud probability for the first transaction;   determining, by the one or more computer devices, that the first fraud probability corresponds to a first fraud classification, defined by a first set of policies associated with a first set of merchants, that differs from a corresponding second fraud classification defined by a second set of policies associated with a second set of merchants;   outputting, by the one or more computer devices, the first fraud classification to a first merchant associated with the first transaction when the first set of merchants includes the first merchant;   receiving, by the one or more computer devices and after outputting the first fraud classification, second transaction data for a second transaction associated with a second consumer that differs from the first consumer;   identifying, by one or more computer devices, a plurality of second transaction attributes associated with the second transaction data;   determining, by the one or more computer devices, that at least one transaction attribute is common to the first transaction attributes and the second transaction attributes;   determining, by the one or more computer devices, a second fraud probability for the first transaction based on the second transaction data; and   outputting, by the one or more computer devices, an updated fraud classification to the first merchant based on the second fraud probability as defined by the first set of policies.   
     
     
         2 . The method of  claim 1 , wherein a second merchant that differs from the first merchant is associated with the second transaction. 
     
     
         3 . The method of  claim 2 , wherein the second set of merchants includes the second merchant and the first set of merchants is associated with a first industry that differs from a second industry associated with the second set of merchants. 
     
     
         4 . The method of  claim 1 , wherein outputting the first fraud classification includes:
 generating a first alert, associated with the first transaction, based on the first fraud classification, wherein the first alert corresponds to a first recommendation that the merchant accept, deny, or fulfill the first transaction, and   outputting the first alert to the first merchant.   
     
     
         5 . The method of  claim 4 , wherein outputting the updated fraud classification includes:
 generating a second alert, associated with the first transaction, based on the updated fraud classification, wherein the second alert corresponds to a second recommendation that the first merchant accept, deny, or fulfill the first transaction,   determining whether the second recommendation differs from the first recommendation, and   outputting the second alert to the first merchant only when the second recommendation differs from the first recommendation.   
     
     
         6 . The method of  claim 5 , wherein the updated fraud classification and the second fraud classification are the same. 
     
     
         7 . The method of  claim 5 , wherein the updated fraud classification differs from the second fraud classification. 
     
     
         8 . A system, comprising:
 a communication interface;   one or more memory devices to store instructions for detecting fraud; and   one or more processors to execute the instructions to:
 receive, via the communication interface, first transaction data for a first transaction associated with a first consumer, 
 identify a plurality of first transaction attributes associated with the first transaction data, 
 determine, based on the first transaction data, a first fraud probability for the first transaction, 
 determine that the first fraud probability corresponds to a first fraud classification, defined by a first set of policies associated with a first set of merchants, that differs from a corresponding second fraud classification defined by a second set of policies associated with a second set of merchants, 
 output, via the communication interface, the first fraud classification to a first merchant associated with the first transaction when the first set of merchants includes the first merchant, 
 receive, via the communication interface and after outputting the first fraud classification, second transaction data for a second transaction associated with a second consumer that differs from the first consumer, 
 identify a plurality of second transaction attributes associated with the second transaction data, 
 determine that at least one transaction attribute is common to the first transaction attributes and the second transaction attributes, 
 determine a second fraud probability for the first transaction based on the second transaction data, and 
   output, via the communication interface, an updated fraud classification to the first merchant based on the second fraud probability as defined by the first set of policies.   
     
     
         9 . The system of  claim 8 , wherein a second merchant that differs from the first merchant is associated with the second transaction. 
     
     
         10 . The system of  claim 9 , wherein the second set of merchants includes the second merchant and the first set of merchants is associated with a first industry that differs from a second industry associated with the second set of merchants. 
     
     
         11 . The method of  claim 8 , wherein the one or more processors execute the instructions to output the first fraud classification by:
 generating a first alert, associated with the first transaction, based on the first fraud classification, wherein the first alert corresponds to a first recommendation that the merchant accept, deny, or fulfill the first transaction, and   outputting the first alert to the first merchant.   
     
     
         12 . The method of  claim 11 , wherein the one or more processors execute the instructions to output the updated fraud classification by:
 generating a second alert, associated with the first transaction, based on the updated fraud classification, wherein the second alert corresponds to a second recommendation that the first merchant accept, deny, or fulfill the first transaction,   determining whether the second recommendation differs from the first recommendation, and   outputting the second alert to the first merchant only when the second recommendation differs from the first recommendation.   
     
     
         13 . The method of  claim 12 , wherein the updated fraud classification and the second fraud classification are the same. 
     
     
         14 . The method of  claim 12 , wherein the updated fraud classification differs from the second fraud classification. 
     
     
         15 . A non-transitory computer-readable medium that stores instructions executable by one or more computer devices to perform a method, comprising:
 receiving, via a communication interface, first transaction data for a first transaction associated with a first consumer;   identifying, by the one or more computer devices, a plurality of first transaction attributes associated with the first transaction data;   determining, by the one or more computer devices and based on the first transaction data, a first fraud probability for the first transaction;   determining, by the one or more computer devices, that the first fraud probability corresponds to a first fraud classification, defined by a first set of policies associated with a first set of merchants, that differs from a corresponding second fraud classification defined by a second set of policies associated with a second set of merchants;   outputting, via the communication interface, the first fraud classification to a first merchant associated with the first transaction when the first set of merchants includes the first merchant;   receiving, via the communication interface and after outputting the first fraud classification, second transaction data for a second transaction associated with a second consumer that differs from the first consumer;   identifying, by one or more computer devices, a plurality of second transaction attributes associated with the second transaction data;   determining, by the one or more computer devices, that at least one transaction attribute is common to the first transaction attributes and the second transaction attributes;   determining, by the one or more computer devices, a second fraud probability for the first transaction based on the second transaction data; and   outputting, via the communication interface, an updated fraud classification to the first merchant based on the second fraud probability as defined by the first set of policies.   
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein a second merchant that differs from the first merchant is associated with the second transaction. 
     
     
         17 . The non-transitory computer-readable medium of  claim 16 , wherein the second set of merchants includes the second merchant and the first set of merchants is associated with a first industry that differs from a second industry associated with the second set of merchants. 
     
     
         18 . The non-transitory computer-readable medium of  claim 15 , wherein outputting the first fraud classification includes:
 generating a first alert, associated with the first transaction, based on the first fraud classification, wherein the first alert corresponds to a first recommendation that the merchant accept, deny, or fulfill the first transaction, and   outputting the first alert to the first merchant.   
     
     
         19 . The method of  claim 18 , wherein outputting the updated fraud classification includes:
 generating a second alert, associated with the first transaction, based on the updated fraud classification, wherein the second alert corresponds to a second recommendation that the first merchant accept, deny, or fulfill the first transaction,   determining whether the second recommendation differs from the first recommendation, and   outputting the second alert to the first merchant only when the second recommendation differs from the first recommendation.   
     
     
         20 . The method of  claim 19 , wherein the updated fraud classification and the second fraud classification are the same.