Systems and methods for generating recommendations using a corpus of data

Abstract

A method and system for recommending a merchant are provided. The method includes receiving financial transaction data documenting financial transactions between a plurality of account holders and a plurality of merchants and generating a merchant correspondence matrix that includes the plurality of merchants and a plurality of indicators of interactions associated with pairs of the plurality of merchants. The plurality of indicators of interactions tallying financial transactions conducted by the plurality of account holders at both of the merchants in a pair of the plurality of merchants. The method further includes receiving a query for a recommendation of a merchant from an account holder and generating a ranked list of merchants based on a recommender algorithm. The recommender algorithm inferring user preferences from attributes of the plurality of merchants that were visited by the cardholder.

1 . A computer-based method for recommending a merchant, the method implemented using a recommender computer device coupled to a memory device, the method comprising:
 receiving financial transaction data documenting financial transactions between a plurality of account holders and a plurality of merchants;   generating a merchant correspondence matrix that includes the plurality of merchants and a plurality of indicators of interactions associated with pairs of the plurality of merchants, the plurality of indicators of interactions tallying financial transactions conducted by the plurality of account holders at both of the merchants in at least one of the pairs of the plurality of merchants;   receiving a query for a recommendation of a merchant from an account holder or other user; and   generating a ranked list of merchants based on a recommender module configured to infer user preferences from attributes of the plurality of merchants that were visited by the account holder.   
     
     
         2 . The computer-based method of  claim 1 , wherein generating the merchant correspondence matrix comprises generating the merchant correspondence matrix by correlating the interactions between each of the plurality of account holders and respective merchants of the plurality of merchants. 
     
     
         3 . The computer-based method of  claim 2 , wherein generating the ranked list of merchants comprises generating the ranked list of merchants based on an express list of user preferences. 
     
     
         4 . The computer-based method of  claim 3 , wherein generating the ranked list of merchants based on the express list of user preferences comprises generating the ranked list of merchants based on user preferences associated with a registered primary account number (PAN) of an account holder's account. 
     
     
         5 . The computer-based method of  claim 3 , wherein generating the ranked list of merchants based on an express list of user preferences comprises generating the ranked list of merchants based on user preferences received from an account holder prior to receiving the query for the recommendation. 
     
     
         6 . The computer-based method of  claim 3 , wherein generating the ranked list of merchants based on an express list of user preferences comprises generating the ranked list of merchants based on user preferences received from an account holder or other user contemporaneously with the query for the recommendation. 
     
     
         7 . The computer-based method of  claim 1 , wherein generating the ranked list of merchants comprises applying a selectable number of iterations of a user preference vector to the merchant correspondence matrix. 
     
     
         8 . The computer-based method of  claim 7 , wherein applying the selectable number of iterations of the user preference vector to the merchant correspondence matrix comprises applying a first amount of activation in the plurality of merchants in the merchant correspondence matrix at the locations previously visited, the first amount of activation increasing the rank of merchants based on the number of previous visits. 
     
     
         9 . The computer-based method of  claim 7 , wherein applying a selectable number of iterations of a user preference vector to the merchant correspondence matrix comprises distributing the first amount of activation through the plurality of merchants in the merchant correspondence matrix. 
     
     
         10 . The computer-based method of  claim 1 , wherein generating the ranked list of merchants comprises:
 generating a first temporary ranked list of merchants based on the merchant correspondence matrix using no expressed user preferences;   generating a second temporary ranked list of merchants based on the merchant correspondence matrix using expressed user preferences;   assigning a merchant's final ranking based on a number of positions the merchant has changed between the second temporary ranked list and the first temporary ranked list.   
     
     
         11 . The computer-based method of  claim 1 , wherein generating the ranked list of merchants comprises:
 creating a first ranked list of merchants for a first metropolitan area;   using a portion of the top ranked merchants to seed a second merchant correspondence matrix; and   creating a second ranked list of merchants for a second metropolitan area using the seeded second merchant correspondence matrix.   
     
     
         12 . A recommender system for recommending a merchant comprises one or more processors communicatively coupled to one or more memory devices, said one or more processors are configured to:
 receive financial transaction data documenting financial transactions between a plurality of account holders and a plurality of merchants;   generate a merchant correspondence matrix that includes the plurality of merchants and a plurality of indicators of interactions associated with pairs of the plurality of merchants, the plurality of indicators of interactions tallying financial transactions conducted by the plurality of account holders at both of the merchants in at least one of the pairs of the plurality of merchants;   receive a query for a recommendation of a merchant from an account holder; and   generate a ranked list of merchants based on a recommender algorithm, the recommender algorithm inferring user preferences from attributes of the plurality of merchants that were visited by the cardholder.   
     
     
         13 . The system of  claim 12 , wherein said one or more processors are configured to generate the merchant correspondence matrix by correlating the interactions between each of the plurality of account holders and respective merchants of the plurality of merchants. 
     
     
         14 . The system of  claim 12 , wherein said one or more processors are configured to generate the ranked list of merchants based on an express list of user preferences. 
     
     
         15 . The system of  claim 12 , wherein said one or more processors are configured to generate the ranked list of merchants based on user preferences associated with a registered primary account number (PAN) of an account holder's account. 
     
     
         16 . One or more non-transitory computer-readable storage media having computer-executable instructions embodied thereon, wherein when executed by at least one processor, the computer-executable instructions cause the processor to:
 receive financial transaction data documenting financial transactions between a plurality of account holders and a plurality of merchants;   generate a merchant correspondence matrix that includes the plurality of merchants and a plurality of indicators of interactions associated with pairs of the plurality of merchants, the plurality of indicators of interactions tallying financial transactions conducted by the plurality of account holders at both of the merchants in at least one of the pairs of the plurality of merchants;   receive a query for a recommendation of a merchant from an account holder; and   generate a ranked list of merchants based on a recommender algorithm, the recommender algorithm inferring user preferences from attributes of the plurality of merchants that were visited by the cardholder.   
     
     
         17 . The computer-readable storage media of  claim 16 , wherein the computer-executable instructions further cause the processor to apply a selectable number of iterations of a user preference vector to the merchant correspondence matrix. 
     
     
         18 . The computer-readable storage media of  claim 17 , wherein the computer-executable instructions further cause the processor to apply a first amount of activation in the plurality of merchants in the merchant correspondence matrix at the locations previously visited, the first amount of activation increasing the rank of merchants based on the number of previous visits. 
     
     
         19 . The computer-readable storage media of  claim 17 , wherein the computer-executable instructions further cause the processor to distribute the first amount of activation through the plurality of merchants in the merchant correspondence matrix. 
     
     
         20 . The computer-readable storage media of  claim 16 , wherein the computer-executable instructions further cause the processor to:
 generate a first temporary ranked list of merchants based on the merchant correspondence matrix using no expressed user preferences;   generate a second temporary ranked list of merchants based on the merchant correspondence matrix using expressed user preferences;   assign a merchant's final ranking based on a number of positions the merchant has changed between the second temporary ranked list and the first temporary ranked list.