Inventors:
- Bloomington IL, US
Elizabeth Flowers - Bloomington IL, US
Reena Batra - Alpharetta GA, US
Miriam Valero - Bloomington IL, US
Puneit Dua - Bloomington IL, US
Shanna L. Phillips - Bloomington IL, US
Russell Ruestman - Minonk IL, US
Bradley A. Craig - Normal IL, US
International Classification:
G06Q 20/40
G06N 99/00
G06N 5/04
Abstract:
A method of identifying a potential chargeback scenario includes generating or updating chargeback candidate detection rules, at least by training a machine learning program. The machine learning program may be trained using transaction data associated with financial transactions, and using chargeback determinations, for the financial transactions, that were made in accordance with chargeback rules associated with a card network entity. The method also includes receiving an indication that fraud has been confirmed for a financial transaction associated with a merchant and a financial account, and retrieving transaction data associated with the financial transaction. The method may further include determining, by applying the chargeback candidate detection rules, that a chargeback may be warranted for the transaction, and causing an indication of such to be displayed to one or more people via one or more computing device user interfaces.