Rules suggestion engine

Abstract

Embodiments of the invention are directed to systems and methods for implementing a rules suggestion engine that suggests rules to a user for lowering fraud in future transactions. Embodiments of the invention segment the transaction data based on at least one attribute defined by the user. One or more key indicators are identified corresponding to the segmented data. A correlation is performed between the user defined attribute and one or more key indicators. One or more transaction rules are generated based on the correlation that are suggested to the user for future transactions. The user can customize the rule, a field of rule, a prioritization of the rules, and even create categories of rules.

1 - 20 . (canceled) 
     
     
         21 . A method comprising:
 segmenting, by a processor, transaction data for a plurality of transactions, wherein the transaction data is segmented based on at least one transaction attribute;   determining a suggested transaction rule based on a correlation between the at least one transaction attribute and the segmented transaction data;   determining a first result of applying the suggested transaction rule to one or more new transactions;   determining a second result of applying a current transaction rule to the one or more new transactions;   based on a comparison of the first result to the second result, determining whether a risk of fraud is reduced for the one or more new transactions; and   in response to determining that the risk of fraud is reduced for the one or more new transactions, modifying a rule profile using the suggested transaction rule.   
     
     
         22 . The method of  claim 21 , wherein applying the suggested transaction rule to the one or more new transactions does not cause the one or more new transactions to be rejected based on the suggested transaction rule. 
     
     
         23 . The method of  claim 21 , wherein the suggested transaction rule is applied to the one or more new transactions occurring during a time period. 
     
     
         24 . The method of  claim 21 , wherein determining whether the risk of fraud is reduced for the one or more new transactions includes comparing a result of the comparison to a threshold, and wherein the risk of fraud is reduced in the event that the result of the comparison satisfies the threshold. 
     
     
         25 . The method of  claim 24 , wherein the threshold is adjusted in the event that the result of the comparison does not satisfy the threshold. 
     
     
         26 . The method of  claim 21 , further comprising:
 in response to determining that the risk of fraud is not reduced for the one or more new transactions, modifying the current transaction rule.   
     
     
         27 . The method of  claim 21 , wherein modifying the rule profile using the suggested transaction rule includes modifying the rule profile based on a value determined from a difference between the suggested transaction rule and the current transaction rule. 
     
     
         28 . The method of  claim 21 , further comprising:
 determining the suggested transaction rule based on a correlation of the transaction attribute to the segmented transaction data, wherein the correlation is determined based on one or more key indicators corresponding to the segmented transaction data.   
     
     
         29 . The method of  claim 21 , further comprising:
 obtaining transaction data from a plurality of transactions.   
     
     
         30 . A server computer comprising:
 a processor; and   a non-transitory computer readable medium coupled to the processor, the computer readable medium comprising code executable by the processor to implement a method comprising:
 segmenting transaction data for a plurality of transactions, wherein the transaction data is segmented based on at least one transaction attribute; 
 determining a suggested transaction rule based on a correlation between the at least one transaction attribute and the segmented transaction data; 
 determining a first result of applying the suggested transaction rule to one or more new transactions; 
 determining a second result of applying a current transaction rule to the one or more new transactions; 
 based on a comparison of the first result to the second result, determining whether a risk of fraud is reduced for the one or more new transactions; and 
 in response to determining that the risk of fraud is reduced for the one or more new transactions, modifying a rule profile using the suggested transaction rule. 
   
     
     
         31 . The server computer of  claim 30 , wherein the method further comprises:
 detecting fraud in subsequent transactions using the modified rule profile.   
     
     
         32 . The server computer of  claim 30 , wherein determining whether the risk of fraud is reduced for the one or more new transactions includes comparing a result of the comparison to a threshold, and wherein the risk of fraud is reduced in the event that the result of the comparison does not satisfy the threshold. 
     
     
         33 . The server computer of  claim 32 , wherein the threshold is adjusted in the event that the result of the comparison does not satisfy the threshold. 
     
     
         34 . The server computer of  claim 30 , wherein the method further comprises:
 in response to determining that the risk of fraud is not reduced for the one or more new transactions, modifying the current transaction rule.   
     
     
         35 . A system comprising:
 the server computer of  claim 30 ; and   a client computer performing operations in communication with the server computer, wherein the operations comprise:
 segmenting transaction data for a plurality of transactions, wherein the transaction data is segmented based on at least one transaction attribute; 
 determining a suggested transaction rule based on a correlation between the at least one transaction attribute and the segmented transaction data; 
 determining a first result of applying the suggested transaction rule to one or more new transactions; 
 determining a second result of applying a current transaction rule to the one or more new transactions; 
 based on a comparison of the first result to the second result, determining whether a risk of fraud is reduced for the one or more new transactions; and 
   in response to determining that the risk of fraud is reduced for the one or more new transactions, modifying a rule profile using the suggested transaction rule.   
     
     
         36 . A method comprising:
 receiving, by a client computer, at least one transaction attribute; and   accessing a server computer by the client computer, wherein the server computer is configured to implement a method comprising:
 segmenting transaction data for a plurality of transactions, wherein the transaction data is segmented based on the at least one transaction attribute; 
 determining a suggested transaction rule based on a correlation between the at least one transaction attribute and the segmented transaction data; 
 determining a first result of applying the suggested transaction rule to one or more new transactions; 
 determining a second result of applying a current transaction rule to the one or more new transactions; 
 based on a comparison of the first result to the second result, determining whether a risk of fraud is reduced for the one or more new transactions; and 
 in response to determining that the risk of fraud is reduced for the one or more new transactions, modifying a rule profile using the suggested transaction rule. 
   
     
     
         37 . The method of  claim 36 , wherein the transaction data is obtained from a plurality of merchants. 
     
     
         38 . The method of  claim 36 , wherein the transaction data comprises historical data for the plurality of transactions. 
     
     
         39 . A client computer comprising:
 a processor; and   a computer readable medium coupled to the processor, the computer readable medium comprising code, executable by the processor for implementing a method comprising:
 receiving at least one transaction attribute; and 
 accessing a server computer, wherein the server computer is configured to implement a method comprising:
 segmenting transaction data for a plurality of transactions, wherein the transaction data is segmented based on the at least one transaction attribute; 
 determining a suggested transaction rule based on a correlation between the at least one transaction attribute and the segmented transaction data; 
 determining a first result of applying the suggested transaction rule to one or more new transactions; 
 determining a second result of applying a current transaction rule to the one or more new transactions; 
 based on a comparison of the first result to the second result, determining whether a risk of fraud is reduced for the one or more new transactions; and 
 in response to determining that the risk of fraud is reduced for the one or more new transactions, modifying a rule profile using the suggested transaction rule. 
 
   
     
     
         40 . The client computer of  claim 39 , wherein the segmented transaction data corresponds to a portion of the plurality of transactions.