MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122941 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'real-time credit card fraud detection using hybrid ai models.'
Inventor(s) include Dr. Baiju B V; Mr. Veera Hari Sai Prasad; and Mr. Golla Bala Ganesh.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a method (100) for real-time credit card fraud detection. The method (100) includes receiving (101) credit card transaction data including transaction amount, merchant information, geographic location, and temporal data. The method (100) further includes preprocessing (102) the transaction data by cleaning missing values, normalizing numerical features, and encoding categorical variables. The method (100) includes extracting (103) features from the preprocessed data and applying (104) a trained hybrid artificial intelligence model to generate a fraud probability score, where the hybrid model includes a Long Short-Term Memory neural network and Random Forest classifier. The method (100) includes comparing (105) the fraud probability score against a predetermined threshold. The method (100) includes flagging (106) the transaction as fraudulent and generating an alert when the score exceeds the threshold, or approving (107) the transaction as legitimate when it does not."
Disclaimer: Curated by HT Syndication.
