Intellectual Property India Publishes Patent Application for 'Scalable UPI Security System: A Hybrid Machine Learning Architecture for Real-Time Fraud Detection Using Supervised-Unsupervised Ensemble Models' Filed by B V Raju Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541124398 A) filed by B V Raju Institute Of Technology, Narsapur, Telangana, on Dec. 10, 2025, for 'scalable upi security system: a hybrid machine learning architecture for real-time fraud detection using supervised-unsupervised ensemble models.'

Inventor(s) include G. Lavanya; K. Usha Sri; Devasoth Saritha; and M. Krishna Prasanna.

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 invention relates to a scalable hybrid machine learning system for detecting fraud in Unified Payments Interface (UPI) transactions. The system integrates gradient-boosted models, LSTM networks, and Isolation Forest to detect both known and novel fraud patterns in real-time. A meta-learning ensemble architecture provides optimal prediction accuracy and low false positives. The system achieves 96.7% detection accuracy and 2,800+ transactions per second processing speed, offering a robust and scalable solution for modern financial cybersecurity."

Disclaimer: Curated by HT Syndication.