Online fraud prevention using genetic algorithm solution

Abstract

Online fraud prevention including receiving a rules set to detect fraud, mapping the rules set to a data set, mapping success data to members of the rules set, filtering the members of the rules set, and ordering members of the data set by giving priority to those members of the data set with a greater probability for being fraudulent based upon the success data of each member of the rule set in detecting fraud. Further, a receiver coupled to an application server to receive a rules set to detect fraud, and a server coupled to the application server, to map the rules set to a data set, and to map the success data to each members of the rules set. The server is used to order the various members of the data set by giving priority to those members of the data set with a greatest probability for being fraudulent.

1 . A system comprising:
 a receiver configured to receive a set of rules for use in detecting fraudulent transactions;   a server, operatively connected to the receiver, the server configured to:
 identify a set of accounts that facilitated the detected fraudulent transactions; 
 access a rule set to identify fraudulent accounts based on a series of transactions; 
 map the rule set to a target set of fraudulent accounts; 
 generate a plurality of rule trees, each rule tree comprising a random combination of rules of the rule set; 
 for each rule tree of the plurality of rule trees, determine a fitness of the rule tree with respect to other rule trees based on applying the rule tree to the target set of fraudulent accounts and tabulating the amount of fraudulent accounts detected by the rule tree; and 
 provide the new rule set to a rules engine of the server according to the fitness of the new rule set. 
   
     
     
         2 . The system of  claim 1 , wherein the server is further configured to generate a tree-form based on the new rule set. 
     
     
         3 . The system of  claim 1 , wherein the server is further configured to genera a set of hash tables based on the new rule set. 
     
     
         4 . The system of  claim 1 , wherein the server is further configured to calculate a success rate of the new rule set in identifying the fraudulent accounts. 
     
     
         5 . The system of  claim 4 , wherein the server is further configured to remove the new rule set if the success rate is below a predefined threshold. 
     
     
         6 . The system of  claim 5 , wherein the removed new rule set is used for the purpose of accruing a hit rate. 
     
     
         7 . The system of  claim 6 , wherein the server is further configured to re-activate the removed new rule set based on a subsequent hit rate. 
     
     
         8 . The system of  claim 1 , wherein the new rule set is generated via crossover or mutation of the respective rules. 
     
     
         9 . The system of  claim 1 , wherein the new rule set is generated to capture data in a predefined set of known fraudulent transactions. 
     
     
         10 . The system of  claim 1 , wherein the server is further configured to order the fraudulent accounts according to a calculated probability for fraud. 
     
     
         11 . A method comprising:
 receiving a set of rules for use in detecting fraudulent transactions;   identifying a set of accounts that facilitated the detected fraudulent transactions;   accessing a rule set to identify fraudulent accounts based on a series of transactions;   mapping the rule set to a target set of fraudulent accounts;   generating a plurality of rule trees, each rule tree comprising a random combination of rules of the rule set;   for each rule tree of the plurality of rule trees, determining a fitness of the rule tree with respect to other rule trees based on applying the rule tree to the target set of fraudulent accounts and tabulating the amount of fraudulent accounts detected by the rule tree; and   providing the new rule set to a rules engine according to the fitness of the new rules set.   
     
     
         12 . The method of  claim 11 , further comprising generating a tree-form based on the new rule set. 
     
     
         13 . The method of  claim 11 , further comprising generating a set of hash tables based on the new rule set. 
     
     
         14 . The method of  claim 11 , further comprising calculating a success rate of the new rule set in identifying the fraudulent accounts. 
     
     
         15 . The method of  claim 14 , further comprising removing the rule set if the success rate is below a predefined threshold. 
     
     
         16 . The method of  claim 15 , wherein the removed new rule set is used for the purpose of accruing a hit rate. 
     
     
         17 . The method of  claim 16 , further comprising re-activating the removed new rule set based on a subsequent hit rate. 
     
     
         18 . A non-transitory computer-readable storage medium having instructions embodied thereon, the instructions executable by a processor to perform operations comprising:
 receiving a set of rules for use in detecting fraudulent transactions;   identifying a set of accounts that facilitated the detected fraudulent transactions;   accessing a rule set to identify fraudulent accounts based on a series of transactions;   mapping the rule set to a target set of fraudulent accounts;   generating a plurality of rule trees, each rule tree comprising a random combination of rules of the rule set;   for each rule tree of the plurality of rule trees, determining a fitness of the rule tree with respect to other rule trees based on applying the rule tree to the target set of fraudulent accounts and tabulating the amount of fraudulent accounts detected by the rule tree; and   providing the new rule set to a rules engine according to the fitness of the new rules set.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 20  wherein the operations further comprise:
 capturing data in a predefined set of known fraudulent transactions to generate the new rule set. 
 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 20  wherein the operations further comprise:
 ordering the fraudulent accounts according to a calculated probability for fraud.