Artificial intelligence-based fraud and risk management methods and systems for acquirers

Patent metadata

Field	Value
Publication number	US-12530690-B2
Application number	US-202318482733-A
Country	US
Kind code	B2
Filing date	Oct 6, 2023
Priority date	Oct 7, 2022
Publication date	Jan 20, 2026
Grant date	Jan 20, 2026

Abstract

Methods and server systems for computing fraud risk scores for various merchants associated with an acquirer described herein. The method performed by a server system includes accessing merchant-related transaction data including merchant-related transaction indicators associated with a merchant from a transaction database. Method includes generating a merchant-related transaction features based on the merchant-related indicators. Method includes generating via risk prediction models, for a payment transaction with the merchant, merchant health and compliance risk scores, merchant terminal risk scores, merchant chargeback risk scores, and merchant activity risk scores based on the merchant-related transaction features. Method includes facilitating transmission of a notification message to an acquirer server associated with the merchant. The notification message includes the merchant health and compliance risk scores, the merchant terminal risk scores, the merchant chargeback risk scores, and the merchant activity risk scores.

First claim

What is claimed is:

1 . A computer-implemented method, comprising:
accessing, by a server system, merchant-related transaction data associated with a merchant from a transaction database associated with the server system, the merchant-related data comprising a set of merchant-related indicators; generating, by the server system, a set of merchant-related transaction features based, at least in part, on the set of merchant-related indicators; generating, by the server system via one or more risk prediction models, for a payment transaction with the merchant, a set of merchant health and compliance risk scores, a set of merchant terminal risk scores, a set of merchant chargeback risk scores, and a set of merchant activity risk scores based, at least in part, on the set of merchant-related transaction features, wherein the one or more risk prediction models comprise a merchant health and compliance risk prediction model, a merchant terminal risk prediction model that is a machine learning model and generates the set of merchant terminal risk scores, a merchant chargeback risk prediction model, and a merchant activity risk prediction model, wherein the set of merchant terminal risk scores includes an indication of whether a terminal comprising a computing device associated with the merchant is unable to read a chip of a payment card to complete a transaction to be less secure; facilitating, by the server system, transmission of a notification message to an acquirer server associated with the merchant, the notification message comprising the set of merchant health and compliance risk scores, the set of merchant terminal risk scores, the set of merchant chargeback risk scores, and the set of merchant activity risk scores; and fix, with the acquirer server, the terminal based on the indication so that the terminal is capable of reading chips of payment cards.

2 . The computer-implemented method as claimed in claim 1 , wherein the set of merchant-related indicators comprises a unique merchant identifier (ID), geo-location data, a payment means, timestamp information, a merchant industry, a merchant country, a merchant state, a merchant city, a merchant location ID, a transaction amount, a fraud transaction amount, a fraud count indicator, a transaction indicator, transaction currency, an acquiring bank, an acquiring country, an issuing bank, an issuing country, a card product type, an electronic commerce (e-commerce) indicator, a contactless payment indicator, a recurring transaction indicator, a user presence indicator, a cross-border transaction indicator, an average card visit indicator, an average card spend indicator, an average online transaction amount indicator, an average Point of Sale (POS) transaction amount indicator, an average cross-border transaction amount indicator, an average contactless transaction amount indicator, an average Personal Identification Number (PIN) transaction amount indicator, an average card present transaction amount indicator, an average transaction amount on card type indicator, a transaction amount ratio indicator, a card decline rate indicator, a fraud-related chargeback indicator, a non-fraud related chargeback indicator, a Merchant Category Code (MCC) risk indicator, a terminal data indicator, and a fallback transaction indicator.

3 . The computer-implemented method as claimed in claim 1 , wherein generating the set of merchant health and compliance risk scores, further comprises:
determining, by the server system, a set of health and compliance-related transaction features based, at least in part, on the set of merchant-related transaction features, the set of health and compliance-related transaction features comprising merchant fraud risk data, ghost merchant risk data, merchant fraud attrition risk data, merchant circumvention risk data, merchant alternative identity data, and merchant account takeover risk data; and generating, by the server system via the merchant health and compliance risk prediction model, the set of merchant health and compliance risk scores based, at least in part, on the set of health and compliance-related transaction features, the set of merchant health and compliance risk scores comprising a merchant fraud risk score, a ghost merchant risk score, a merchant fraud attrition risk score, a merchant circumvention risk score, a merchant alternative identity score, and a merchant account takeover risk score.

4 . The computer-implemented method as claimed in claim 1 , wherein generating the set of merchant terminal risk scores, further comprises:
determining, by the server system, a set of terminal-related transaction features based, at least in part, on the set of merchant-related transaction features, the set of terminal-related transaction features comprising chip failure data, terminal fraud attack risk data, and terminal information compromise data; and generating, by the server system via the merchant terminal risk prediction model, the set of merchant terminal risk scores based, at least in part, on the set of terminal-related transaction features, the set of merchant terminal risk scores comprising a chip failure risk score, a terminal fraud attack risk score, and a terminal information compromise score.

5 . The computer-implemented method as claimed in claim 4 , wherein generating the set of merchant chargeback risk scores, further comprises:
determining, by the server system, a set of chargeback-related transaction features based, at least in part, on the set of merchant-related transaction features, the set of chargeback-related transaction features comprising fraud chargeback risk data, fraud chargeback Gross Dollar Value (GDV) data, and excessive return risk data; and generating, by the server system via the merchant chargeback risk prediction model, the set of merchant chargeback risk scores based, at least in part, on the set of terminal-related transaction features, the set of merchant chargeback risk prediction scores comprising a fraud chargeback risk score, a fraud chargeback GDV risk score, and an excessive return risk score.

6 . The computer-implemented method as claimed in claim 4 , wherein generating the set of merchant activity risk scores, further comprises:
determining, by the server system, a set of activity related transaction features based, at least in part, on the set of merchant-related transaction features, the set of activity related transaction features comprises contactless adoption likelihood data, contactless adoption revenue data, contactless growth likelihood data, contactless growth revenue data, anomalous ticket risk data, anomalous time risk data, and anomalous sales risk data; and generating, by the server system via the merchant activity risk prediction model, the set of merchant activity risk scores based, at least in part, on the set of terminal-related transaction features, the set of merchant activity risk scores comprising a fraud contactless adoption likelihood score, a contactless adoption revenue score, a contactless growth likelihood score, a contactless growth revenue score, an anomalous ticket risk score, an anomalous time risk score, and an anomalous sales risk score.

7 . The computer-implemented method as claimed in claim 1 , further comprising:
receiving, by the server system, an authentication request message for the payment transaction between a cardholder and the merchant from the acquirer server.

8 . The computer-implemented method as claimed in claim 1 , wherein facilitating the transmission of the notification message, further comprises:
generating, by the server system, an updated authorization response message for the payment transaction based, at least in part, on an authorization response message associated with th

Assignees

• Mastercard International Inc

Inventors

• Gupta Smriti
• Patankar Adarsh
• Choudhary Akash
• Bhatraju Alekhya
• Khan Ammar Ahmad
• Kundu Amrita
• Saraswat Ankur
• Gupta Anubhav
• Kumar Awanish
• Agarwal Ayush
• Mcguigan Brian M
• Das Debasmita
• Yadav Deepak
• Shrivastava Diksha
• Arora Garima
• Dhama Gaurav
• Oberoi Gaurav
• Waghmare Govind Vitthal
• Wadhwa Hardik
• Peretta Jessica
• Goyal Kanishk
• Prasad Karthik
• Vusse Lekhana
• Singh Maneet
• Gulla Niranjan
• Kumar Nitish
• Ranjan Rajesh Kumar
• Ganesh V Ram
• Bhattacharya Rohit
• Sankhala Rupesh Kumar
• Asthana Siddhartha
• Ghosh Soumyadeep
• Bhaduri Sourojit
• Tiwari Srijita
• Powar Suhas
• Skelsey Susan

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q30/0609

  Qualifying participants for shopping transactions (payment transaction verification G06Q20/401) · CPC title

• G06Q30/018

  Certifying business or products · CPC title

• G06Q10/0635

  Risk analysis of enterprise or organisation activities · CPC title