System, Method, and Computer Program Product for Evaluating a Fraud Detection System

Abstract

Provided are methods that include determining a set of transaction related actions for an agent, selecting a first transaction related action from the set of transaction related actions for the agent based on a plurality of features associated with the agent, generating transaction data associated with a fraudulent transaction based on the first transaction related action, generating a feature vector, the feature vector including transaction data associated with the fraudulent transaction, providing the feature vector as an input to a fraud detection machine learning model. Methods may also include determining an output of the fraud detection machine learning model based on the feature vector as the input, and generating a fraudulent reward parameter for the first transaction related action based on the output of the fraud detection machine learning model. Systems and computer program products are also provided.

What is claimed is: 
     
         1 . A system, comprising:
 at least one processor programmed or configured to:
 select a first transaction related action from a set of transaction related actions for an agent based on a plurality of features associated with the agent, wherein the agent comprises a simulated adversarial actor that is designed to engage in fraudulent conduct involving an account of a user, wherein each transaction related action comprises an action associated with conducting a payment transaction by the agent, and wherein, when selecting the first transaction related action from the set of transaction related actions for the agent, the at least one processor is programmed or configured to:
 determine the plurality of features associated with the agent based on one or more historical payment transactions of a plurality of historical payment transactions involving the account of the user; and 
 select the first transaction related action from the set of transaction related actions for the agent based on an agent action machine learning model and the plurality of features associated with the agent, wherein the first transaction related action is an output of the agent action machine learning model based on the plurality of features associated with the agent; 
 provide a feature vector as an input to a fraud detection machine learning model; 
 determine an output of the fraud detection machine learning model based on the feature vector as the input; and 
 update a weight parameter of the agent action machine learning model based on the output of the fraud detection machine learning model. 
 
   
     
     
         2 . The system of  claim 1 , wherein the at least one processor is further programmed or configured to:
 generate a plurality of status indicators regarding fraudulent transaction outcomes associated with transaction related actions performed by the agent based on transaction data associated with the plurality of historical payment transactions, wherein each status indicator comprises an indication of a status of each historical payment transaction as being a fraudulent transaction or a non-fraudulent transaction, and   generate a feature vector based on transaction data associated with the plurality of historical payment transactions, wherein the transaction data associated with the plurality of historical payment transactions comprises the plurality of status indicators, wherein the feature vector comprises transaction data associated with the fraudulent transaction, and wherein the fraudulent transaction is a fraudulent transaction of the plurality of historical payment transactions.   
     
     
         3 . The system of  claim 1 , wherein the at least one processor is further programmed or configured to:
 generate a set of transaction related actions for the agent based on historical transaction data associated with the one or more historical transactions.   
     
     
         4 . The system of  claim 1 , wherein the at least one processor is further programmed or configured to:
 update the agent action machine learning model based on a fraudulent reward parameter for another transaction related action.   
     
     
         5 . The system of  claim 1 , wherein, when determining the plurality of features associated with the agent based on one or more historical payment transactions of a plurality of historical payment transactions, the at least one processor is programmed or configured to:
 determine the plurality of features associated with the agent based on one or more previously-processed fraudulent payment transactions involving an account of a user.   
     
     
         6 . The system of  claim 1 , wherein the at least one processor is further programmed or configured to:
 generate transaction data associated with a fraudulent transaction based on the first transaction related action;   add the transaction data associated with the fraudulent transaction to a training data set of the fraud detection machine learning model; and   retrain the fraud detection machine learning model using the training data set.   
     
     
         7 . The system of  claim 1 , wherein the at least one processor is programmed or configured to:
 generate a plurality of fraudulent reward parameters for a sequence of transaction related actions based on a plurality of outputs of the fraud detection machine learning model;   determine a fraudulent reward amount based on the plurality of fraudulent reward parameters;   assign the fraudulent reward amount to the sequence of transaction related actions; and   store the fraudulent reward amount and the sequence of transaction related actions in a data structure.   
     
     
         8 . A method, comprising:
 selecting, with at least one processor, a first transaction related action from a set of transaction related actions for an agent based on a plurality of features associated with the agent, wherein the agent comprises a simulated adversarial actor that is designed to engage in fraudulent conduct involving an account of a user, wherein each transaction related action comprises an action associated with conducting a payment transaction by the agent, and wherein selecting the first transaction related action from the set of transaction related actions for the agent comprises:
 determining the plurality of features associated with the agent based on one or more historical payment transactions of a plurality of historical payment transactions involving the account of the user; and 
 selecting the first transaction related action from the set of transaction related actions for the agent based on an agent action machine learning model and the plurality of features associated with the agent, wherein the first transaction related action is an output of the agent action machine learning model based on the plurality of features associated with the agent; 
   providing, with at least one processor, a feature vector as an input to a fraud detection machine learning model;   determining, with at least one processor, an output of the fraud detection machine learning model based on the feature vector as the input; and   updating, with at least one processor, a weight parameter of the agent action machine learning model based on the output of the fraud detection machine learning model.   
     
     
         9 . The method of  claim 8 , further comprising:
 generating, with at least one processor, a plurality of status indicators regarding fraudulent transaction outcomes associated with transaction related actions performed by the agent based on transaction data associated with the plurality of historical payment transactions, wherein each status indicator comprises an indication of a status of each historical payment transaction as being a fraudulent transaction or a non-fraudulent transaction, and   generating a feature vector based on transaction data associated with the plurality of historical payment transactions, wherein the transaction data associated with the plurality of historical payment transactions comprises the plurality of status indicators, wherein the feature vector comprises transaction data associated with the fraudulent transaction, and wherein the fraudulent transaction is a fraudulent transaction of the plurality of historical payment transactions.   
     
     
         10 . The method of  claim 8 , further comprising:
 generating a set of transaction related actions for the agent based on historical transaction data associated with the one or more historical transactions.   
     
     
         11 . The method of  claim 8 , further comprising:
 updating the agent action machine learning model based on a fraudulent reward parameter for another transaction related action.   
     
     
         12 . The method of  claim 8 , wherein determining the plurality of features associated with the agent based on one or more historical payment transactions of a plurality of historical payment transactions comprises:
 determining the plurality of features associated with the agent based on one or more previously-processed fraudulent payment transactions involving an account of a user.   
     
     
         13 . The method of  claim 8 , further comprising:
 generating transaction data associated with a fraudulent transaction based on the first transaction related action;   adding the transaction data associated with the fraudulent transaction to a training data set of the fraud detection machine learning model; and   retraining the fraud detection machine learning model using the training data set.   
     
     
         14 . The method of  claim 8 , further comprising:
 generating a plurality of fraudulent reward parameters for a sequence of transaction related actions based on a plurality of outputs of the fraud detection machine learning model;   determining a fraudulent reward amount based on the plurality of fraudulent reward parameters;   assigning the fraudulent reward amount to the sequence of transaction related actions; and   storing the fraudulent reward amount and the sequence of transaction related actions in a data structure.   
     
     
         15 . A computer program product comprising at least one non-transitory computer-readable medium comprising one or more instructions that, when executed by at least one processor, cause the at least one processor to:
 select a first transaction related action from a set of transaction related actions for an agent based on a plurality of features associated with the agent, wherein the agent comprises a simulated adversarial actor that is designed to engage in fraudulent conduct involving an account of a user, wherein each transaction related action comprises an action associated with conducting a payment transaction by the agent, and wherein, the one or more instructions that cause the at least one processor to select the first transaction related action from the set of transaction related actions for the agent, cause the at least one processor to:
 determine the plurality of features associated with the agent based on one or more historical payment transactions of a plurality of historical payment transactions involving the account of the user; and 
 select the first transaction related action from the set of transaction related actions for the agent based on an agent action machine learning model and the plurality of features associated with the agent, wherein the first transaction related action is an output of the agent action machine learning model based on the plurality of features associated with the agent; 
   provide a feature vector as an input to a fraud detection machine learning model;   determine an output of the fraud detection machine learning model based on the feature vector as the input; and   update a weight parameter of the agent action machine learning model based on the output of the fraud detection machine learning model.   
     
     
         16 . The computer program product of  claim 15 , wherein the one or more instructions further cause the at least one processor to:
 generate a plurality of status indicators regarding fraudulent transaction outcomes associated with transaction related actions performed by the agent based on transaction data associated with the plurality of historical payment transactions, wherein each status indicator comprises an indication of a status of each historical payment transaction as being a fraudulent transaction or a non-fraudulent transaction, and   generate a feature vector based on transaction data associated with the plurality of historical payment transactions, wherein the transaction data associated with the plurality of historical payment transactions comprises the plurality of status indicators, wherein the feature vector comprises transaction data associated with the fraudulent transaction, and wherein the fraudulent transaction is a fraudulent transaction of the plurality of historical payment transactions.   
     
     
         17 . The computer program product of  claim 15 , wherein the one or more instructions further cause the at least one processor to:
 generate a set of transaction related actions for the agent based on historical transaction data associated with the one or more historical transactions.   
     
     
         18 . The computer program product of  claim 15 , wherein the one or more instructions further cause the at least one processor to:
 update the agent action machine learning model based on a fraudulent reward parameter for another transaction related action.   
     
     
         19 . The computer program product of  claim 15 , wherein, the one or more instructions that cause the at least one processor to determine the plurality of features associated with the agent based on one or more historical payment transactions of a plurality of historical payment transactions, cause the at least one processor to:
 determine the plurality of features associated with the agent based on one or more previously-processed fraudulent payment transactions involving an account of a user.   
     
     
         20 . The computer program product of  claim 15 , wherein the one or more instructions further cause the at least one processor to:
 generate transaction data associated with a fraudulent transaction based on the first transaction related action;   add the transaction data associated with the fraudulent transaction to a training data set of the fraud detection machine learning model; and   retrain the fraud detection machine learning model using the training data set.