Intellectual Property India Publishes Patent Application for A Machine Learning-Based System And Method For Credit Card Transaction Fraud Detection

MUMBAI, India, Oct. 12 -- Intellectual Property India has published a patent application (202641118911 A) filed by Mlr Institute Of Technology; and Marri Laxman Reddy Institute Of Technology And Management on October 05, 2026, for A Machine Learning-Based System And Method For Credit Card Transaction Fraud Detection.

Inventors include Mrs. V. Divya; Ms. R. Nishita; Mr. Varun Sandesh; Mr. V. Ram Charan; and Mr. D. Durga Prasad.

The application for the patent was published on October 09, 2026, under issue no. 41/2026.

Abstract: The present invention relates to a machine learning-based system and method for detecting potentially fraudulent credit card transactions. The system is configured to receive transaction data comprising one or more transaction attributes including transaction amount, transaction time, transaction location, merchant information, and user transaction behaviour. A data processing module preprocesses the received transaction data and generates transaction features for analysis. A machine learning module analyses the generated features using one or more trained machine learning models and identifies deviations from learned transaction patterns and behavioural characteristics. A classification module classifies each transaction into one or more predefined categories comprising genuine, suspicious, or fraudulent based on an obtained fraud likelihood or classification result. An alert generation module is configured to generate a notification when a transaction satisfies a predefined fraud detection condition. The system further comprises a monitoring interface for presenting transaction information, classification results, and generated alerts to an authorised user. The machine learning module can be trained using historical transaction datasets containing legitimate and fraudulent transaction records and can be updated using subsequently processed transaction data. The system is configured to process individual or multiple transaction records and provide automated fraud detection based on transaction characteristics and learned behavioural patterns, thereby providing a computer-implemented mechanism for identifying potentially fraudulent credit card transactions.

Disclaimer: Curated by HT Syndication.