Initiating cardswap based on analytic model indicating third party card reissuance

Abstract

Various embodiments are directed to initiating or triggering a cardswap action for a customer based on a determination that one or more third-party cards associated with the customer have likely been reissued. The determination may be based on the analysis performed by an analytics model on customer transaction data corresponding to the customer. The analytics model may be trained using various patterns, trends, or characteristics observed in the customer transaction data around a timeframe of an actual reissue event. When a likely reissue event has been determined, one or more customer cards may be presented to the customer for swapping out the reissued third-party cards with a customer card.

What is claimed is: 
     
         1 . A method, comprising:
 receiving, by a processor, transaction data associated with a customer;   identifying, by a machine learning (ML) model executing on the processor based at least in part on the transaction data, an event for a third-party card associated with the customer;   identifying, by the processor, a first card associated with the customer;   identifying, by the processor based on the transaction data, a plurality of third-party websites where the third-party card is stored to process payments; and   automatically performing a cardswap by the processor based on the identification of the first card, wherein the performance of the cardswap comprises executing a script to:
 navigate, by a web browser executing on the processor, to each identified third-party website; and 
 replace, using the web browser, the third-party card on file at each identified third-party website with the first card by populating an account number of the first card into a respective form field on each identified third-party website. 
   
     
     
         2 . The method of  claim 1 , wherein the event comprises one or more of: (i) an alteration of an account number associated with the third-party card, (ii) an alteration of an expiration date associated with the third-party card, (iii) an alteration of a security code associated with the third-party card, or (iv) a change in one or more spending attributes of the third-party card within a predetermined time interval. 
     
     
         3 . The method of  claim 1 , wherein the ML model is trained based on transaction data associated with a plurality of customers, the plurality of customers including the customer, wherein the transaction data associated with the plurality of customers comprises: (i) data reflecting a change in spending patterns for each customer, (ii) data reflecting a change in spending volume for each customer, (iii) data reflecting a respective increase in a frequency of use of a card by each customer, (iv) data reflecting a first purchase by each customer with a merchant, (v) data reflecting one or more recurring charges for each customer. 
     
     
         4 . The method of  claim 1 , wherein the ML model comprises a classification model, wherein the script is executed by a browser extension of the web browser. 
     
     
         5 . The method of  claim 1 , further comprising:
 presenting at least the first card to the customer; and   receiving input selecting the first card.   
     
     
         6 . The method of  claim 1 , wherein the performance of the cardswap further comprises executing the script to:
 determine another third-party website does not include payment token information; and   refrain from populating the account number into the form field on the another third-party website based on the determination that the another third-party website does not include payment token information.   
     
     
         7 . The method of  claim 1 , wherein the first card is identified based on one or more of: (i) an available balance of the first card, (ii) an expiration date of the first card, (iii) a spending pattern of the first card, (iv) a use of the first card increasing from a first time interval to a second time interval. 
     
     
         8 . A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a processor, cause the processor to:
 receive transaction data associated with a customer;   identify, by a machine learning (ML) model executing based at least in part on the transaction data, an event for a third-party card associated with the customer;   identify a first card associated with the customer;   identify, based on the transaction data, a plurality of third-party websites where the third-party card is stored to process payments; and   automatically perform a cardswap based on the identification of the first card, wherein the performance of the cardswap comprises executing a script to:
 navigate, by a web browser, to each identified third-party website; and 
 replace, via the web browser, the third-party card on file at each identified third-party website with the first card by populating an account number of the first card into a respective form field on each identified third-party website. 
   
     
     
         9 . The computer-readable storage medium of  claim 8 , wherein the event comprises one or more of: (i) an alteration of an account number associated with the third-party card, (ii) an alteration of an expiration date associated with the third-party card, (iii) an alteration of a security code associated with the third-party card, or (iv) a change in one or more spending attributes of the third-party card within a predetermined time interval. 
     
     
         10 . The computer-readable storage medium of  claim 8 , wherein the ML model is trained based on transaction data associated with a plurality of customers, the plurality of customers include the customer, wherein the transaction data associated with the plurality of customers comprises: (i) data reflecting a change in spending patterns for each customer, (ii) data reflecting a change in spending volume for each customer, (iii) data reflecting a respective increase in a frequency of use of a card by each customer, (iv) data reflecting a first purchase by each customer with a merchant, (v) data reflecting one or more recurring charges for each customer. 
     
     
         11 . The computer-readable storage medium of  claim 8 , wherein the ML model comprises a classification model, wherein the script is executed by a browser extension of the web browser. 
     
     
         12 . The computer-readable storage medium of  claim 8 , wherein the instructions further cause the processor to:
 present at least the first card to the customer; and   receive input select the first card.   
     
     
         13 . The computer-readable storage medium of  claim 8 , wherein the performance of the cardswap further comprises executing the script to:
 determine another third-party website does not include payment token information; and   refrain from populating the account number into the form field on the another third-party website based on the determination that the another third-party website does not include payment token information.   
     
     
         14 . The computer-readable storage medium of  claim 8 , wherein the first card is identified based on one or more of: (i) an available balance of the first card, (ii) an expiration date of the first card, (iii) a spending pattern of the first card, (iv) a use of the first card increasing from a first time interval to a second time interval. 
     
     
         15 . A computing apparatus comprising:
 a processor; and   a memory storing instructions that, when executed by the processor, cause the processor to:
 receive transaction data associated with a customer; 
 identify, by a machine learning (ML) model executing based at least in part on the transaction data, an event for a third-party card associated with the customer; 
 identify a first card associated with the customer; 
 identify, based on the transaction data, a plurality of third-party websites where the third-party card is stored to process payments; and 
   automatically perform a cardswap based on the identification of the first card, wherein the performance of the cardswap comprises executing a script to:
 navigate, by a web browser, to each identified third-party website; and 
 replace, via the web browser, the third-party card on file at each identified third-party website with the first card by populating an account number of the first card into a respective form field on each identified third-party website. 
   
     
     
         16 . The computing apparatus of  claim 15 , wherein the event comprises one or more of: (i) an alteration of an account number associated with the third-party card, (ii) an alteration of an expiration date associated with the third-party card, (iii) an alteration of a security code associated with the third-party card, or (iv) a change in one or more spending attributes of the third-party card within a predetermined time interval. 
     
     
         17 . The computing apparatus of  claim 15 , wherein the ML model is trained based on transaction data associated with a plurality of customers, the plurality of customers include the customer, wherein the transaction data associated with the plurality of customers comprises: (i) data reflecting a change in spending patterns for each customer, (ii) data reflecting a change in spending volume for each customer, (iii) data reflecting a respective increase in a frequency of use of a card by each customer, (iv) data reflecting a first purchase by each customer with a merchant, (v) data reflecting one or more recurring charges for each customer. 
     
     
         18 . The computing apparatus of  claim 15 , wherein the ML model comprises a classification model, wherein the script is executed by a browser extension of the web browser. 
     
     
         19 . The computing apparatus of  claim 15 , wherein the performance of the cardswap further comprises executing the script to:
 determine another third-party website does not include payment token information; and   refrain from populating the account number into the form field on the another third-party website based on the determination that the another third-party website does not include payment token information.   
     
     
         20 . The computing apparatus of  claim 15 , wherein the first card is identified based on one or more of: (i) an available balance of the first card, (ii) an expiration date of the first card, (iii) a spending pattern of the first card, (iv) a use of the first card increasing from a first time interval to a second time interval.