Abstract
The present disclosure provides Methods, systems, and computer program products for predicting disputed transactions may: obtain transaction-level data associated with one or more prior transactions associated with an account identifier, account-level data associated with the account identifier, and merchant-level data associated with one or more merchants associated with the one or more prior transactions associated with the account identifier; and train a machine learning model, by: providing, as input to the machine learning model, the transaction-level data, the account-level data, and the merchant-level data; receiving, as output from the machine learning model, a prediction of a next transaction associated with the account identifier, identifier, wherein the prediction includes an indication of whether the next transaction associated with the account identifier is predicted to be a disputed transaction; and modifying, using a loss function that depends on the prediction, one or more parameters of the machine learning model.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
LUONG, TRAM; WENG, JENNY; GUNDA, SAI THRINATH; YANG, JING; DAS, RAJAT; DAVIS, ROBERT; and STOPIC, RICHARD, "METHOD AND SYSTEM FOR PREDICTING A SMART DISPUTE SCORE", Technical Disclosure Commons, (February 19, 2024)
https://www.tdcommons.org/dpubs_series/6696