System, method, and non-transitory computer-readable storage media for recommending merchants

Abstract

A computer system for recommending merchants to a candidate cardholder is provided. The computer system includes a memory device and a processor. The processor receives transaction information for a plurality of cardholders from a payment network. The transaction information includes data relating to purchases made by the cardholders at a plurality of merchants, where the purchases satisfy a first criteria. The processor also receives candidate cardholder preference information for at least one of the merchants input by the candidate cardholder. The processor further determines a merchant rank for each merchant based on the received transaction information and the candidate cardholder preference information, and determines a neutral merchant rank for each merchant based on the received transaction information and neutral cardholder preferences of the plurality of cardholders. The processor also determines a merchant score for each of the plurality of merchants by comparing the merchant rank to the neutral merchant rank.

What is claimed is: 
     
         1 . A computer system comprising a memory device for storing data, and at least one processor in communication with the memory device and a payment network, the at least one processor configured to:
 receive, from the payment network, data including electronic payment transaction information for a plurality of electronic payment transactions involving a plurality of accountholders including a candidate accountholder and a plurality of merchants;   identify, from the electronic payment transaction information, a subset of accountholders from the plurality of accountholders, each of the subset of accountholders having completed electronic payment transactions with at least two of the plurality of merchants;   create, based on the electronic payment transaction information associated with the subset of accountholders, a merchant popularity matrix, wherein the merchant popularity matrix is a data structure that indicates a number of transactions associated with the at least two merchants;   apply the merchant popularity matrix to a candidate accountholder preference vector of the candidate accountholder to create a candidate accountholder merchant ranking vector;   determine a merchant score vector based on a difference between the candidate accountholder merchant ranking vector and a general merchant ranking vector, wherein the merchant score vector includes a merchant score associated with each merchant of the plurality of merchants;   create a list of recommended merchants by sorting the merchant score vector based on the merchant score of each merchant; and   provide content configured to cause the list of recommended merchants to be displayed through an application executing on a user device of the candidate accountholder.   
     
     
         2 . The computer system of  claim 1 , wherein the at least one processor is further configured to generate, based upon a predetermined region, a subset of the electronic payment transaction information of the plurality of electronic payment transactions involving at least some of the plurality of accountholders and a subset of merchants of the plurality of merchants located within the predetermined region. 
     
     
         3 . The computer system of  claim 2 , wherein the at least two merchants are located within the predetermined region. 
     
     
         4 . The computer system of  claim 1 , wherein the at least one processor is further configured to create the merchant popularity matrix by incrementing the number of transactions when an accountholder in the subset of accountholders completes multiple electronic payment transactions at the at least two merchants, and wherein, to reduce an effect of accountholder bias toward a single merchant, the number of transactions in the merchant popularity matrix is not incremented when the accountholder completes more than one electronic payment transactions at a same merchant. 
     
     
         5 . The computer system of  claim 1 , wherein the at least one processor is further configured to:
 receive, from the application executing on the user device, input data including preference data of the candidate accountholder, wherein the user device is in communication with the processor via the application, wherein the input data is entered into the application by the candidate accountholder on the user device, and wherein the preference data represents preferences of the candidate accountholder for particular merchants of the plurality of merchants; and   determine the candidate accountholder preference vector of the candidate accountholder based upon the received input data.   
     
     
         6 . The computer system of  claim 1 , wherein the at least one processor is further configured to apply the merchant popularity matrix to a neutral preference vector to create the general merchant ranking vector. 
     
     
         7 . The computer system of  claim 1 , wherein the at least one processor is further configured to identify the plurality of merchants as registered to use the payment network. 
     
     
         8 . A computer-implemented method implemented using a computer system including a memory device for storing data, and at least one processor in communication with the memory device and a payment network, the method comprising:
 receiving, from the payment network, data including electronic payment transaction information for a plurality of electronic payment transactions involving a plurality of accountholders including a candidate accountholder and a plurality of merchants;   identifying, from the electronic payment transaction information, a subset of accountholders from the plurality of accountholders, each of the subset of accountholders having completed electronic payment transactions with at least two of the plurality of merchants;   creating, based on the electronic payment transaction information associated with the subset of accountholders, a merchant popularity matrix, wherein the merchant popularity matrix is a data structure that indicates a number of transactions associated with the at least two merchants;   applying the merchant popularity matrix to a candidate accountholder preference vector of the candidate accountholder to create a candidate accountholder merchant ranking vector;   determining a merchant score vector based on a difference between the candidate accountholder merchant ranking vector and a general merchant ranking vector, wherein the merchant score vector includes a merchant score associated with each merchant of the plurality of merchants;   creating a list of recommended merchants by sorting the merchant score vector based on the merchant score of each merchant; and   providing content configured to cause the list of recommended merchants to be displayed through an application executing on a user device of the candidate accountholder.   
     
     
         9 . The method of  claim 8  further comprising generating, based upon a predetermined region, a subset of the electronic payment transaction information of the plurality of electronic payment transactions involving at least some of the plurality of accountholders and a subset of merchants of the plurality of merchants located within the predetermined region. 
     
     
         10 . The method of  claim 9 , wherein the at least two merchants are located within the predetermined region. 
     
     
         11 . The method of  claim 8  further comprising creating the merchant popularity matrix by incrementing the number of transactions when an accountholder in the subset of accountholders completes multiple electronic payment transactions at the at least two merchants, and wherein, to reduce an effect of accountholder bias toward a single merchant, the number of transactions in the merchant popularity matrix is not incremented when the accountholder completes more than one electronic payment transactions at a same merchant. 
     
     
         12 . The method of  claim 8  further comprising:
 receiving, from the application executing on the user device, input data including preference data of the candidate accountholder, wherein the user device is in communication with the processor via the application, wherein the input data is entered into the application by the candidate accountholder on the user device, and wherein the preference data represents preferences of the candidate accountholder for particular merchants of the plurality of merchants; and 
 determining the candidate accountholder preference vector of the candidate accountholder based upon the received input data. 
 
     
     
         13 . The method of  claim 8  further comprising applying the merchant popularity matrix to a neutral preference vector to create the general merchant ranking vector. 
     
     
         14 . The method of  claim 8  further comprising identifying the plurality of merchants as registered to use the payment network. 
     
     
         15 . One or more non-transitory computer-readable storage media having computer-executable instructions embodied thereon, wherein when executed by at least one processor in communication with a payment network and a memory device for storing data, the computer-executable instructions cause the at least one processor to:
 receive, from the payment network, data including electronic payment transaction information for a plurality of electronic payment transactions involving a plurality of accountholders including a candidate accountholder and a plurality of merchants;   identify, from the electronic payment transaction information, a subset of accountholders from the plurality of accountholders, each of the subset of accountholders having completed electronic payment transactions with at least two of the plurality of merchants;   create, based on the electronic payment transaction information associated with the subset of accountholders, a merchant popularity matrix, wherein the merchant popularity matrix is a data structure that indicates a number of transactions associated with the at least two merchants;   apply the merchant popularity matrix to a candidate accountholder preference vector of the candidate accountholder to create a candidate accountholder merchant ranking vector;   determine a merchant score vector based on a difference between the candidate accountholder merchant ranking vector and a general merchant ranking vector, wherein the merchant score vector includes a merchant score associated with each merchant of the plurality of merchants;   create a list of recommended merchants by sorting the merchant score vector based on the merchant score of each merchant; and   provide content configured to cause the list of recommended merchants to be displayed through an application executing on a user device of the candidate accountholder.   
     
     
         16 . The non-transitory computer-readable storage media of  claim 15 , wherein the computer-executable instructions cause the at least one processor to generate, based upon a predetermined region, a subset of the electronic payment transaction information of the plurality of electronic payment transactions involving at least some of the plurality of accountholders and a subset of merchants of the plurality of merchants located within the predetermined region. 
     
     
         17 . The non-transitory computer-readable storage media of  claim 15 , wherein the computer-executable instructions cause the at least one processor to create the merchant popularity matrix by incrementing the number of transactions when an accountholder in the subset of accountholders completes multiple electronic payment transactions at the at least two merchants, and wherein, to reduce an effect of accountholder bias toward a single merchant, the number of transactions in the merchant popularity matrix is not incremented when the accountholder completes more than one electronic payment transactions at a same merchant. 
     
     
         18 . The non-transitory computer-readable storage media of  claim 15 , wherein the computer-executable instructions cause the at least one processor to:
 receive, from the application executing on the user device, input data including preference data of the candidate accountholder, wherein the user device is in communication with the processor via the application, wherein the input data is entered into the application by the candidate accountholder on the user device, and wherein the preference data represents preferences of the candidate accountholder for particular merchants of the plurality of merchants; and   determine the candidate accountholder preference vector of the candidate accountholder based upon the received input data.   
     
     
         19 . The non-transitory computer-readable storage media of  claim 15 , wherein the computer-executable instructions cause the at least one processor to apply the merchant popularity matrix to a neutral preference vector to create the general merchant ranking vector. 
     
     
         20 . The non-transitory computer-readable storage media of  claim 15 , wherein the computer-executable instructions cause the at least one processor to identify the plurality of merchants as registered to use the payment network.