System, Method, and Computer Program Product for Determining a Dominant Account Profile of an Account

Abstract

Provided are methods for determining a dominant account profile of an account. The method may include receiving transaction data associated with a plurality of payment transactions conducted within a predetermined time interval of activation of an account involved in the plurality of payment transactions, generating a dominant account profile classification model, determining a plurality of prediction scores for the account based on the dominant account profile classification model and the transaction data, where determining the plurality of prediction scores includes determining, for the user, a prediction score for each dominant account profile, where a prediction score includes a prediction of whether the user will conduct a threshold value of payment transactions using the account in one or more payment transaction categories of a plurality of payment transaction categories, and communicating data associated with the plurality of prediction scores. Systems and computer program products are also disclosed.

What is claimed is: 
     
         1 . A system, comprising:
 at least one processor programmed or configured to:
 receive transaction data associated with a plurality of payment transactions conducted within a predetermined time interval after activation of a debit account involved in the plurality of payment transactions; 
 generate a dominant account profile classification model, wherein the dominant account profile classification model is configured to provide an output that includes a prediction as to whether an account will be used to conduct a threshold value of payment transactions in one or more payment transaction categories of a plurality of payment transaction categories during the predetermined time interval, and wherein, when generating the dominant account profile classification model, the at least one processor is programmed or configured to:
 process the transaction data to obtain training data for the dominant account profile classification model, wherein, when processing the transaction data, the at least one processor is programmed or configured to:
 determine a set of transaction variables based on the transaction data, wherein the set of transaction variables comprises: 
  a first account activation variable associated with whether a first payment transaction was conducted in a first payment transaction category of the plurality of payment transaction categories, and 
  a second account activation variable associated with a specific number of the plurality of payment transaction categories in which a second payment transaction was conducted; 
 identify a subset of the set of the transaction variables for determining a probability that a threshold value of payment transactions may be conducted in the one or more payment transaction categories of the plurality of payment transaction categories; and 
 change the transaction data into a format to be analyzed to generate the dominant account profile classification model; 
 
 validate the dominant account profile classification model based on the formatted transaction data and the dominant account profile classification model; 
 
 determine a plurality of prediction scores for an account of a user based on the dominant account profile classification model and the transaction data, wherein, when determining the plurality of prediction scores, the at least one processor is programmed or configured to:
 determine, for the user, a prediction score for each dominant account profile of a plurality of dominant account profiles, wherein the prediction score for a dominant account profile comprises a prediction of whether the account of the user will be used to conduct the threshold value of payment transactions in the one or more payment transaction categories of the plurality of payment transaction categories; and 
 determine a highest prediction score of the plurality of prediction scores for the plurality of dominant account profiles, wherein the highest prediction score corresponds to a recommended dominant account profile of the plurality of dominant account profiles for the account of the user; 
 
 generate an offer from a merchant based on determining that the prediction score of the recommended dominant account profile satisfies a threshold value of the prediction score; and 
 transmit the offer to a user device of the user. 
   
     
     
         2 . The system of  claim 1 , wherein the dominant account profile classification model comprises a multinomial classification model. 
     
     
         3 . The system of  claim 1 , wherein the plurality of dominant account profiles comprises:
 a first dominant account profile associated with the first payment transaction category, the first payment transaction category comprising a first threshold value of payment transactions conducted during the predetermined time interval using a card-not-present payment channel independent of one or more merchant categories,   a second dominant account profile associated with a second payment transaction category, the second payment transaction category comprising a second threshold value of payment transactions conducted during the predetermined time interval in a fuel merchant category, a food and grocery merchant category, a telecommunications and utilities merchant category, a quick service restaurant (QSR) merchant category, and a drug store and pharmacy merchant category,   a third dominant account profile associated with a third payment transaction category, the third payment transaction category comprising a third threshold value of payment transactions conducted during the predetermined time interval in a restaurants merchant category, an apparel and accessories merchant category, a discount store merchant category, a department store merchant category, a retail goods merchant category, an entertainment merchant category, and an electronics merchant category,   a fourth dominant account profile associated with a fourth payment transaction category, the fourth payment transaction category comprising a fourth threshold value of payment transactions conducted during the predetermined time interval in a transportation merchant category, a lodging merchant category, a travel services merchant category, an airlines merchant category, and a vehicle rental merchant category, and   a fifth dominant account profile associated with a fifth payment transaction category, the fifth payment transaction category comprising a fifth threshold value of payment transactions conducted during the predetermined time interval in a health care merchant category, an education and government merchant category, a retail services merchant category, an automotive merchant category, a professional services merchant category, a business-to-business merchant category, a direct marketing merchant category, and a wholesale club merchant category.   
     
     
         4 . The system of  claim 1 , wherein the at least one processor is further programmed or configured to:
 generate new training data based on whether the user conducted the payment transaction involving the account of the user and the offer within the predetermined time interval.   
     
     
         5 . The system of  claim 4 , wherein the at least one processor is further programmed or configured to:
 update the dominant account profile classification model based on the new training data.   
     
     
         6 . The system of  claim 1 , wherein the transaction data is first transaction data associated with a first plurality of payment transactions, and wherein the at least one processor is further programmed or configured to:
 determine second transaction data associated with a second plurality of payment transactions involving a plurality of accounts of a plurality of users;   segment the second plurality of payment transactions into one or more dominant account profiles of the plurality of dominant account profiles based on the transaction data associated with the second plurality of payment transactions; and   identify a dominant account profile for each account of the plurality of accounts based on segmenting the second plurality of payment transactions into the one or more dominant account profiles of the plurality of dominant account profiles.   
     
     
         7 . The system of  claim 1 , wherein the predetermined time interval after activation of the debit account is 30 days. 
     
     
         8 . A method, comprising:
 receiving, with at least one processor, transaction data associated with a plurality of payment transactions conducted within a predetermined time interval after activation of a debit account involved in the plurality of payment transactions;   generating, with the at least one processor, a dominant account profile classification model, wherein the dominant account profile classification model is configured to provide an output that includes a prediction as to whether an account will be used to conduct a threshold value of payment transactions in one or more payment transaction categories of a plurality of payment transaction categories during the predetermined time interval, and wherein generating the dominant account profile classification model comprises:
 processing the transaction data to obtain training data for the dominant account profile classification model, wherein processing the transaction data comprises:
 determining a set of transaction variables based on the transaction data, wherein the set of transaction variables comprises:
 a first account activation variable associated with whether a first payment transaction was conducted in a first payment transaction category of the plurality of payment transaction categories, and 
 a second account activation variable associated with a specific number of the plurality of payment transaction categories in which a second payment transaction was conducted; 
 
 identifying a subset of the set of the transaction variables for determining a probability that a threshold value of payment transactions may be conducted in the one or more payment transaction categories of the plurality of payment transaction categories; and 
 changing the transaction data into a format to be analyzed to generate the dominant account profile classification model; 
 
 validating the dominant account profile classification model based on the formatted transaction data and the dominant account profile classification model; 
   determining, with the at least one processor, a plurality of prediction scores for an account of a user based on the dominant account profile classification model and the transaction data, wherein determining the plurality of prediction scores comprises:
 determining for the user, a prediction score for each dominant account profile of a plurality of dominant account profiles, wherein the prediction score for a dominant account profile comprises a prediction of whether the account of the user will be used to conduct the threshold value of payment transactions in the one or more payment transaction categories of the plurality of payment transaction categories; and 
 determining, with the at least one processor, a highest prediction score of the plurality of prediction scores for the plurality of dominant account profiles, wherein the highest prediction score corresponds to a recommended dominant account profile of the plurality of dominant account profiles for the account of the user; 
   generating, with the at least one processor, an offer from a merchant based on determining that the prediction score of the recommended dominant account profile satisfies a threshold value of the prediction score; and   transmitting, with the at least one processor, the offer to a user device of the user.   
     
     
         9 . The method of  claim 8 , wherein the dominant account profile classification model comprises a multinomial classification model. 
     
     
         10 . The method of  claim 8 , wherein the plurality of dominant account profiles comprises:
 a first dominant account profile associated with the first payment transaction category, the first payment transaction category comprising a first threshold value of payment transactions conducted during the predetermined time interval using a card-not-present payment channel independent of one or more merchant categories,   a second dominant account profile associated with a second payment transaction category, the second payment transaction category comprising a second threshold value of payment transactions conducted during the predetermined time interval in a fuel merchant category, a food and grocery merchant category, a telecommunications and utilities merchant category, a quick service restaurant (QSR) merchant category, and a drug store and pharmacy merchant category,   a third dominant account profile associated with a third payment transaction category, the third payment transaction category comprising a third threshold value of payment transactions conducted during the predetermined time interval in a restaurants merchant category, an apparel and accessories merchant category, a discount store merchant category, a department store merchant category, a retail goods merchant category, an entertainment merchant category, and an electronics merchant category,   a fourth dominant account profile associated with a fourth payment transaction category, the fourth payment transaction category comprising a fourth threshold value of payment transactions conducted during the predetermined time interval in a transportation merchant category, a lodging merchant category, a travel services merchant category, an airlines merchant category, and a vehicle rental merchant category, and   a fifth dominant account profile associated with a fifth payment transaction category, the fifth payment transaction category comprising a fifth threshold value of payment transactions conducted during the predetermined time interval in a health care merchant category, an education and government merchant category, a retail services merchant category, an automotive merchant category, a professional services merchant category, a business-to-business merchant category, a direct marketing merchant category, and a wholesale club merchant category.   
     
     
         11 . The method of  claim 8 , further comprising:
 generating new training data based on whether the user conducted the payment transaction involving the account of the user and the offer within the predetermined time interval.   
     
     
         12 . The method of  claim 11 , further comprising:
 updating the dominant account profile classification model based on the new training data.   
     
     
         13 . The method of  claim 8 , wherein the transaction data is first transaction data associated with a first plurality of payment transactions, and the method further comprising:
 determining second transaction data associated with a second plurality of payment transactions involving a plurality of accounts of a plurality of users;   segmenting the second plurality of payment transactions into one or more dominant account profiles of the plurality of dominant account profiles based on the transaction data associated with the second plurality of payment transactions; and   identifying a dominant account profile for each account of the plurality of accounts based on segmenting the second plurality of payment transactions into the one or more dominant account profiles of the plurality of dominant account profiles.   
     
     
         14 . The method of  claim 8 , wherein the predetermined time interval after activation of the debit account is 30 days. 
     
     
         15 . A computer program product, the computer program product comprising at least one non-transitory computer-readable medium including one or more instructions that, when executed by at least one processor, cause the at least one processor to:
 receive transaction data associated with a plurality of payment transactions conducted within a predetermined time interval after activation of a debit account involved in the plurality of payment transactions;   generate a dominant account profile classification model, wherein the dominant account profile classification model is configured to provide an output that includes a prediction as to whether an account will be used to conduct a threshold value of payment transactions in one or more payment transaction categories of a plurality of payment transaction categories during the predetermined time interval, and wherein the one or more instructions that cause the at least one processor to generate the dominant account profile classification model, cause the at least one processor to:
 process the transaction data to obtain training data for the dominant account profile classification model, wherein, the one or more instructions that cause the at least one processor to processing the transaction data, cause the at least one processor to:
 determine a set of transaction variables based on the transaction data, wherein the set of transaction variables comprises:
 a first account activation variable associated with whether a first payment transaction was conducted in a first payment transaction category of the plurality of payment transaction categories, and 
 a second account activation variable associated with a specific number of the plurality of payment transaction categories in which a second payment transaction was conducted; 
 
 identify a subset of the set of the transaction variables for determining a probability that a threshold value of payment transactions may be conducted in the one or more payment transaction categories of the plurality of payment transaction categories; and 
 change the transaction data into a format to be analyzed to generate the dominant account profile classification model; 
 
 validate the dominant account profile classification model based on the formatted transaction data and the dominant account profile classification model; 
   determine a plurality of prediction scores for an account of a user based on the dominant account profile classification model and the transaction data, wherein, the one or more instructions that cause the at least one processor to determine the plurality of prediction scores, cause the at least one processor to:
 determine, for the user, a prediction score for each dominant account profile of a plurality of dominant account profiles, wherein the prediction score for a dominant account profile comprises a prediction of whether the account of the user will be used to conduct the threshold value of payment transactions in the one or more payment transaction categories of the plurality of payment transaction categories; and 
 determine a highest prediction score of the plurality of prediction scores for the plurality of dominant account profiles, wherein the highest prediction score corresponds to a recommended dominant account profile of the plurality of dominant account profiles for the account of the user; 
   generate an offer from a merchant based on determining that the prediction score of the recommended dominant account profile satisfies a threshold value of the prediction score; and   transmit the offer to a user device of the user.   
     
     
         16 . The computer program product of  claim 15 , wherein the dominant account profile classification model comprises a multinomial classification model. 
     
     
         17 . The computer program product of  claim 15 , wherein the plurality of dominant account profiles comprises:
 a first dominant account profile associated with the first payment transaction category, the first payment transaction category comprising a first threshold value of payment transactions conducted during the predetermined time interval using a card-not-present payment channel independent of one or more merchant categories,   a second dominant account profile associated with a second payment transaction category, the second payment transaction category comprising a second threshold value of payment transactions conducted during the predetermined time interval in a fuel merchant category, a food and grocery merchant category, a telecommunications and utilities merchant category, a quick service restaurant (QSR) merchant category, and a drug store and pharmacy merchant category,   a third dominant account profile associated with a third payment transaction category, the third payment transaction category comprising a third threshold value of payment transactions conducted during the predetermined time interval in a restaurants merchant category, an apparel and accessories merchant category, a discount store merchant category, a department store merchant category, a retail goods merchant category, an entertainment merchant category, and an electronics merchant category,   a fourth dominant account profile associated with a fourth payment transaction category, the fourth payment transaction category comprising a fourth threshold value of payment transactions conducted during the predetermined time interval in a transportation merchant category, a lodging merchant category, a travel services merchant category, an airlines merchant category, and a vehicle rental merchant category, and   a fifth dominant account profile associated with a fifth payment transaction category, the fifth payment transaction category comprising a fifth threshold value of payment transactions conducted during the predetermined time interval in a health care merchant category, an education and government merchant category, a retail services merchant category, an automotive merchant category, a professional services merchant category, a business-to-business merchant category, a direct marketing merchant category, and a wholesale club merchant category.   
     
     
         18 . The computer program product of  claim 15 , wherein the one or more instructions further cause the at least one processor to:
 generate new training data based on whether the user conducted the payment transaction involving the account of the user and the offer within the predetermined time interval.   
     
     
         19 . The computer program product of  claim 18 , wherein the one or more instructions further cause the at least one processor to:
 update the dominant account profile classification model based on the new training data.   
     
     
         20 . The computer program product of  claim 15 , wherein the transaction data is first transaction data associated with a first plurality of payment transactions, and wherein the one or more instructions further cause the at least one processor to:
 determine second transaction data associated with a second plurality of payment transactions involving a plurality of accounts of a plurality of users;   segment the second plurality of payment transactions into one or more dominant account profiles of the plurality of dominant account profiles based on the transaction data associated with the second plurality of payment transactions; and   identify a dominant account profile for each account of the plurality of accounts based on segmenting the second plurality of payment transactions into the one or more dominant account profiles of the plurality of dominant account profiles.