CPC G06Q 20/3674 (2013.01) [G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06Q 20/4016 (2013.01); G06Q 20/405 (2013.01)] | 21 Claims |
1. A computer-implemented method comprising:
obtaining, by a computing device, transaction data comprising a plurality of transactions associated with a first user;
analyzing, using a machine learning model, the transaction data by comparing the transaction data to a spend profile associated with the first user, wherein the spend profile comprises information indicating a typical spend amount associated with the first user;
using the machine learning model and based on the analyzing, identifying as a candidate multi-party transaction, a first transaction, of the plurality of transactions, having a transaction amount greater, by a threshold amount, than the typical spend amount associated with the first user;
generating, using the machine learning model and based on the spend profile, a confidence metric indicating a likelihood that the candidate multi-party transaction is a multi-party transaction, wherein the multi-party transaction comprises a transaction for a purchase shared with one or more other parties;
generating, by the computing device, a payment token for the multi-party transaction, wherein the payment token comprises a uniform resource locator (URL) link to access information on a plurality of delegation requests associated with the first transaction;
transmitting, to a user device associated with the first user and based on the confidence metric exceeding a threshold value, a notification indicating identification of the multi-party transaction; and
transmitting, to one or more devices associated with the one or more other parties, a delegation request comprising the payment token, wherein the delegation request comprises information indicating a portion of the transaction amount that the first user request payment from the one or more other parties.
|