US 11,900,387 B2
Monitoring account usage to provide transaction retry notifications
Lisa-Marie Braun, New Rochelle, NY (US); and Zachary Nusbaum, Long Island City, NY (US)
Assigned to MASTERCARD INTERNATIONAL INCORPORATED, Purchase, NY (US)
Filed by MASTERCARD INTERNATIONAL INCORPORATED, Purchase, NY (US)
Filed on Oct. 20, 2020, as Appl. No. 17/075,090.
Prior Publication US 2022/0122076 A1, Apr. 21, 2022
Int. Cl. G06Q 40/02 (2023.01); G06Q 20/40 (2012.01); G06Q 20/08 (2012.01); G06N 20/00 (2019.01); G06Q 20/12 (2012.01); G06Q 20/02 (2012.01)
CPC G06Q 20/405 (2013.01) [G06N 20/00 (2019.01); G06Q 20/02 (2013.01); G06Q 20/085 (2013.01); G06Q 20/127 (2013.01); G06Q 20/4037 (2013.01); G06Q 40/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for providing transaction retry notifications, the system comprising:
at least one processor; and
at least one memory storing computer program code that when executed by the at least one processor causes the at least one processor to perform operations of:
receiving an insufficient funds message of a first transaction, wherein the insufficient funds message indicates that the first transaction includes a payment to be provided to a merchant from an account and that the account has insufficient funds to provide the payment to the merchant;
storing an account identifier of the account associated with the first transaction in a monitored account identifier data set;
detecting a successful transaction message of a second transaction associated with the account based on the stored account identifier in the monitored account identifier data set, the second transaction being initiated after the first transaction;
upon detecting the successful transaction message, calculating a confidence factor of a retry attempt of the first transaction, wherein the confidence factor indicates a likelihood that the retry attempt will be successful;
based on the calculated confidence factor exceeding a confidence threshold, sending a transaction retry notification to the merchant;
receiving a retry of the first transaction from the merchant after sending the transaction retry notification; and
training, using a machine learning module comprising a trained regressor that is trained based on merchant feedback indicating whether the retry was successful, an account usage model.