Split up a single transaction into many transactions based on category spend

Abstract

Aspects described herein may relate to techniques for segmenting one transaction into multiple sub-transactions. A user may wish to purchase multiple items. The overall purchase request may be segmented into multiple sub-transactions based on a transaction category of each item. Transaction categories may be based on merchant category codes (MCCs). Each sub-transaction may include one or more items related to the same transaction category. Each sub-transaction may be underwritten and approved separately by the merchant and/or a financial institution (e.g., a credit card company). Financial information related to each different transaction category may be determined based on the sub-transactions. Reward offers may be provided in a more robust manner based on the different transaction categories determined during the purchase process.

What is claimed is: 
     
         1 . A method comprising:
 generating a trained machine learning model by training, using training data comprising a plurality of different items and a corresponding merchant category code for each of the plurality of different items, a machine learning model to output merchant category codes in response to input item indications;   accessing a plurality of different e-mails associated with an e-mail account of a user;   determining, by processing the plurality of different e-mails, a first e-mail associated with a transaction;   processing text of the first e-mail using a natural language processing algorithm to identify a plurality of different indications of items purchased via the transaction;   providing, as input to the trained machine learning model, the plurality of different indications of the items purchased via the transaction;   receiving, as output from the trained machine learning model and in response to the input, a plurality of different merchant category codes, each corresponding to a different item of the items purchased via the transaction;   dividing the transaction into a plurality of different portions of the transaction by determining:
 a first portion of the transaction corresponding to a first merchant category code of the plurality of different merchant category codes; and 
 
a second portion of the transaction corresponding to a second merchant category code of the plurality of different merchant category codes;
 determining a quantity of reward points for each portion of the plurality of different portions of the transaction based on a corresponding merchant category code of each portion of the plurality of different portions of the transaction; and 
 causing, based on a first quantity of reward points for the first portion of the transaction, output of a user interface associated with a reward offer. 
 
     
     
         2 . The method of  claim 1 , wherein the plurality of different indications of items purchased via the transaction indicates a first item of a first transaction category and a second item of a second transaction category. 
     
     
         3 . The method of  claim 1 , wherein at least one indication of the plurality of different indications of items purchased via the transaction comprises an item name. 
     
     
         4 . The method of  claim 1 , further comprising:
 receiving, via a point of sale system, indications of a plurality of items for purchase by a user based on a barcode of each item of the plurality of items; and   generating, based on the indications of the plurality of items, the first e-mail.   
     
     
         5 . The method of  claim 4 , further comprising:
 sending, to the e-mail account of the user, the first e-mail.   
     
     
         6 . The method of  claim 1 , further comprising:
 causing a point of sale system to separately conduct each of the plurality of different portions of the transaction.   
     
     
         7 . The method of  claim 1 , further comprising:
 storing, in a database, an association between the plurality of different merchant category codes and one or more of the items purchased via the transaction.   
     
     
         8 . A computing device comprising:
 one or more processors; and   memory storing instructions that, when executed by the one or more processors, cause the computing device to:
 generate a trained machine learning model by training, using training data comprising a plurality of different items and a corresponding merchant category code for each of the plurality of different items, a machine learning model to output merchant category codes in response to input item indications; 
 access a plurality of different e-mails associated with an e-mail account of a user; 
 determine, by processing the plurality of different e-mails, a first e-mail associated with a transaction; 
 process text of the first e-mail using a natural language processing algorithm to identify a plurality of different indications of items purchased via the transaction; 
 provide, as input to the trained machine learning model, the plurality of different indications of the items purchased via the transaction; 
 receive, as output from the trained machine learning model and in response to the input, a plurality of different merchant category codes, each corresponding to a different item of the items purchased via the transaction; 
 divide the transaction into a plurality of different portions of the transaction by determining:
 a first portion of the transaction corresponding to a first merchant category code of the plurality of different merchant category codes; and 
 
 
a second portion of the transaction corresponding to a second merchant category code of the plurality of different merchant category codes;
 determine a quantity of reward points for each portion of the plurality of different portions of the transaction based on a corresponding merchant category code of each portion of the plurality of different portions of the transaction; and 
 cause, based on a first quantity of reward points for the first portion of the transaction, output of a user interface associated with a reward offer. 
 
     
     
         9 . The computing device of  claim 8 , wherein the plurality of different indications of items purchased via the transaction indicates a first item of a first transaction category and a second item of a second transaction category. 
     
     
         10 . The computing device of  claim 8 , wherein at least one indication of the plurality of different indications of items purchased via the transaction comprises an item name. 
     
     
         11 . The computing device of  claim 8 , wherein the instructions, when executed by the one or more processors, further cause the computing device to:
 receive, via a point of sale system, indications of a plurality of items for purchase by a user based on a barcode of each item of the plurality of items; and   generate, based on the indications of the plurality of items, the first e-mail.   
     
     
         12 . The computing device of  claim 11 , wherein the instructions, when executed by the one or more processors, further cause the computing device to:
 send, to the e-mail account of the user, the first e-mail.   
     
     
         13 . The computing device of  claim 8 , wherein the instructions, when executed by the one or more processors, further cause the computing device to:
 cause a point of sale system to separately conduct each of the plurality of different portions of the transaction.   
     
     
         14 . The computing device of  claim 8 , wherein the instructions, when executed by the one or more processors, further cause the computing device to:
 store, in a database, an association between the plurality of different merchant category codes and one or more of the items purchased via the transaction.   
     
     
         15 . One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors of a computing device, cause the computing device to:
 generate a trained machine learning model by training, using training data comprising a plurality of different items and a corresponding merchant category code for each of the plurality of different items, a machine learning model to output merchant category codes in response to input item indications;   access a plurality of different e-mails associated with an e-mail account of a user;   determine, by processing the plurality of different e-mails, a first e-mail associated with a transaction;   process text of the first e-mail using a natural language processing algorithm to identify a plurality of different indications of items purchased via the transaction;   provide, as input to the trained machine learning model, the plurality of different indications of the items purchased via the transaction;   receive, as output from the trained machine learning model and in response to the input, a plurality of different merchant category codes, each corresponding to a different item of the items purchased via the transaction;   divide the transaction into a plurality of different portions of the transaction by determining:   a first portion of the transaction corresponding to a first merchant category code of the plurality of different merchant category codes; and 
a second portion of the transaction corresponding to a second merchant category code of the plurality of different merchant category codes;
 determine a quantity of reward points for each portion of the plurality of different portions of the transaction based on a corresponding merchant category code of each portion of the plurality of different portions of the transaction; and 
 cause, based on a first quantity of reward points for the first portion of the transaction, output of a user interface associated with a reward offer. 
 
     
     
         16 . The one or more non-transitory computer-readable media of  claim 15 , wherein the plurality of different indications of items purchased via the transaction indicates a first item of a first transaction category and a second item of a second transaction category. 
     
     
         17 . The one or more non-transitory computer-readable media of  claim 15 , wherein at least one indication of the plurality of different indications of items purchased via the transaction comprises an item name. 
     
     
         18 . The one or more non-transitory computer-readable media of  claim 15 , wherein the instructions, when executed by the one or more processors, further cause the computing device to:
 receive, via a point of sale system, indications of a plurality of items for purchase by a user based on a barcode of each item of the plurality of items; and   generate, based on the indications of the plurality of items, the first e-mail.   
     
     
         19 . The one or more non-transitory computer-readable media of  claim 18 , wherein the instructions, when executed by the one or more processors, further cause the computing device to:
 send, to the e-mail account of the user, the first e-mail.   
     
     
         20 . The one or more non-transitory computer-readable media of  claim 15 , wherein the instructions, when executed by the one or more processors, further cause the computing device to:
 cause a point of sale system to separately conduct each of the plurality of different portions of the transaction.