MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122169 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'financial fraud detection system using autoencoder and trust scoring.'
Inventor(s) include Dr. J. Vijayashree; Mr. Dhyey Bhatt; Mr. Harsh Kumar; and Mr. Aditya Krishna.
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 financial fraud detection system including a data ingestion module configured to receive transaction data from financial institutions, a data preprocessing module configured to clean, normalize, and extract features from the transaction data, an autoencoder-based anomaly detection module having an encoder configured to compress transaction features into a latent representation and a decoder configured to reconstruct original transaction features, wherein the autoencoder-based anomaly detection module is trained on non-fraudulent transaction data and configured to calculate reconstruction errors, a trust score calculation module configured to maintain trust profiles and compute trust scores for entities involved in transactions, a decision engine configured to integrate reconstruction errors with trust scores to classify transactions as genuine, suspicious, or fraudulent, and an alert generation module configured to generate fraud alerts for suspicious or fraudulent transactions, wherein the system processes transactions in real-time."
Disclaimer: Curated by HT Syndication.
