Multi-layered credit card with transaction-dependent source selection

Abstract

Techniques are described herein for selecting an optimal financial account for a financial transaction. In an embodiment, a multi-account payment card is used to initiate a financial transaction. Transaction information of the financial transaction including a multi-account payment card ID is transmitted to a server for processing. The server determines that the multi-account payment card ID is associated with a plurality of financial accounts, wherein each of the plurality of financial accounts is associated with any one of a credit card, a debit card, an automatic teller machine (ATM) card, a gift card, or a credit line. A financial account of the plurality of financial accounts is selected by the server based on financial account information, such as anomalous transactions, associated with the plurality of financial accounts and the transaction information of the financial transaction. The financial transaction is then charged to the selected financial account.

What is claimed is: 
     
         1 . A computer-implemented method for selecting a financial account for a financial transaction, comprising:
 inputting into an unsupervised machine learning model financial account information of a plurality of financial accounts of a consumer including information about previous financial transactions performed by the consumer that initiated the financial transaction;   receiving transaction information of the financial transaction at a payment intermediary computer system, the financial transaction involving a multi-account payment card associated with a multi-account payment card identification (ID) of the consumer;   determining, by the payment intermediary computer system, that the multi-account payment card ID is associated with the plurality of financial accounts of the consumer;   wherein each of the plurality of financial accounts is associated with a distinct payment source;   wherein the plurality of financial accounts includes a first financial account designated for use with anomaly transactions;   wherein an anomaly transaction is a financial transaction of the consumer that is determined by the unsupervised machine learning model to be unlike the previous financial transactions performed by the consumer using the plurality of financial accounts;   in response to determining that the multi-account payment card ID is associated with the plurality of financial accounts, selecting, by the intermediary computer system, the first financial account of the plurality of financial accounts based, at least in part, on: 
 inputting into the unsupervised machine learning model information about the financial transaction; 
 determining, using the unsupervised machine learning model, that the financial transaction is an anomaly transaction because the financial transaction is unlike the previous financial transactions performed by the consumer, using the plurality of financial accounts, that were input into the unsupervised machine learning model; and 
 based on the unsupervised machine learning model determining that the financial transaction is an anomaly transaction, selecting the first financial account of the plurality of financial accounts; and 
   causing the intermediary computer system to use the first account to complete the financial transaction.   
     
     
         2 . The method of  claim 1 , wherein:
 receiving transaction information of the financial transaction comprises receiving the transaction information from a first financial computing device associated with the multi-account payment card; and   the computing device associated with the first financial account is a second financial computing device different from the first financial computing device.   
     
     
         3 . The method of  claim 1 , wherein:
 receiving transaction information of the financial transaction comprises receiving the transaction information from a first financial computing device associated with the multi-account payment card; and   the computing device associated with the first financial account is a banking computing device different from the first financial computing device.   
     
     
         4 . The method of  claim 1 , wherein:
 the information about the previous financial transactions performed by the consumer includes amounts of the previous financial transactions;   the information about the financial transaction includes an amount of the financial transaction; and   the unsupervised machine learning model determines the financial transaction is an anomaly transaction by determining that the amount of the financial transaction is outside a threshold value of a mean amount for the previous financial transactions.   
     
     
         5 . The method of  claim 1 , wherein the unsupervised machine learning model uses k-means clustering, mixture models, hierarchical clustering, Neural Networks, autoencoders, Deep Belief Nets, Hebbian Learning, Generative Adversarial Networks, or self-organizing maps. 
     
     
         6 . The method of  claim 1 , wherein determining that the multi-account payment card ID is associated with a plurality of financial accounts of the consumer comprises querying a database to determine the plurality of financial accounts associated with the multi-account payment card ID. 
     
     
         7 . The method of  claim 1 , further comprising:
 before causing the financial transaction to be charged to the first financial account, generating and displaying, at a computing device associated with the consumer, an interface that allows the consumer to provide consent to charge the financial transaction to the first financial account.   
     
     
         8 . The method of  claim 1 , further comprising:
 generating, based on the financial transaction being charged to the first financial account, a digital receipt indicating that the financial transaction was charged to the first financial account; and   transmitting the digital receipt to a computing device associated with the consumer.   
     
     
         9 . The method of  claim 8 , wherein the digital receipt includes explanatory information that provides an explanation of why the first financial account of the plurality of financial accounts was selected. 
     
     
         10 . The method of  claim 8 , wherein the digital receipt includes an interface that allows a consumer to provide feedback information regarding the selection of the first financial account. 
     
     
         11 . One or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause:
 inputting into an unsupervised machine learning model financial account information of a plurality of financial accounts of a consumer including information about previous financial transactions performed by the consumer that initiated the financial transaction;   receiving transaction information of the financial transaction at a payment intermediary computer system, the financial transaction involving a multi-account payment card associated with a multi-account payment card identification (ID) of the consumer;   determining, by the payment intermediary computer system, that the multi-account payment card ID is associated with the plurality of financial accounts of the consumer;   wherein each of the plurality of financial accounts is associated with a distinct payment source;   wherein the plurality of financial accounts includes a first financial account designated for use with anomaly transactions;   wherein an anomaly transaction is a financial transaction of the consumer that is determined by the unsupervised machine learning model to be unlike the previous financial transactions performed by the consumer using the plurality of financial accounts;   in response to determining that the multi-account payment card ID is associated with the plurality of financial accounts, selecting, by the intermediary computer system, the first financial account of the plurality of financial accounts based, at least in part, on: 
 inputting into the unsupervised machine learning model information about the financial transaction; 
 determining, using the unsupervised machine learning model, that the financial transaction is an anomaly transaction because the financial transaction is unlike the previous financial transactions performed by the consumer, using the plurality of financial accounts, that were input into the unsupervised machine learning model; and 
 based on the unsupervised machine learning model determining that the financial transaction is an anomaly transaction, selecting the first financial account of the plurality of financial accounts; and 
   causing the intermediary computer system to use the first account to complete the financial transaction.   
     
     
         12 . The one or more non-transitory computer-readable media of  claim 11 , wherein:
 receiving transaction information of the financial transaction comprises receiving the transaction information from a first financial computing device associated with the multi-account payment card; and   the computing device associated with the first financial account is a second financial computing device different from the first financial computing device.   
     
     
         13 . The one or more non-transitory computer-readable media of  claim 11 , wherein:
 receiving transaction information of the financial transaction comprises receiving the transaction information from a first financial computing device associated with the multi-account payment card; and   the computing device associated with the first financial account is a banking computing device different from the first financial computing device.   
     
     
         14 . The one or more non-transitory computer-readable media of  claim 11 , wherein:
 the information about the previous financial transactions performed by the consumer includes amounts of the previous financial transactions;   the information about the financial transaction includes an amount of the financial transaction; and   the unsupervised machine learning model determines the financial transaction is an anomaly transaction by determining that the amount of the financial transaction is outside a threshold value of a mean amount for the previous financial transactions.   
     
     
         15 . The one or more non-transitory computer-readable media of  claim 11 , wherein the unsupervised machine learning model uses k-means clustering, mixture models, hierarchical clustering, Neural Networks, autoencoders, Deep Belief Nets, Hebbian Learning, Generative Adversarial Networks, or self-organizing maps. 
     
     
         16 . The one or more non-transitory computer-readable media of  claim 11 , wherein determining that the multi-account payment card ID is associated with a plurality of financial accounts of the consumer comprises querying a database to determine the plurality of financial accounts associated with the multi-account payment card ID. 
     
     
         17 . The one or more non-transitory computer-readable media of  claim 11 , further comprising:
 before causing the financial transaction to be charged to the first financial account, generating and displaying, at a computing device associated with the consumer, an interface that allows the consumer to provide consent to charge the financial transaction to the first financial account.   
     
     
         18 . The one or more non-transitory computer-readable media of  claim 11 , further comprising:
 generating, based on the financial transaction being charged to the first financial account, a digital receipt indicating that the financial transaction was charged to the first financial account; and   transmitting the digital receipt to a computing device associated with the consumer.   
     
     
         19 . The one or more non-transitory computer-readable media of  claim 18 , wherein the digital receipt includes explanatory information that provides an explanation of why the first financial account of the plurality of financial accounts was selected. 
     
     
         20 . The one or more non-transitory computer-readable media of  claim 18 , wherein the digital receipt includes an interface that allows a consumer to provide feedback information regarding the selection of the first financial account.