MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043831 A) filed by KKR & KSR Institute of Technology and Sciences, Guntur, Andhra Pradesh, on April 6, for 'machine learning-driven fraud detection and risk analysis system for digital financial transactions.'
Inventor(s) include Dr. D. Harikrishna; Mr. P. Srihari Rao; Ms. P. Anusha; Ms. P. Keerthisri; Ms. M. Bhanuja Chowdary; and Ms. M. Laasya.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "The rapid adoption of digital payment systems in India, particularly the Unified Payments Interface (UPI), has significantly increased transaction convenience while also exposing users to rising fraud risks. Conventional fraud detection techniques often struggle to identify sophisticated and evolving fraudulent patterns. To address these challenges, this project proposes a machine learning-based fraud detection system using ensemble learning algorithms such as XGBoost, LightGBM. Historical UPI transaction data is analyzed in tabular form, enabling the models to capture complex, non-linear relationships and subtle anomalies associated with fraudulent transactions. Once trained, these machine learning models can automatically adapt to emerging fraud techniques, continuously improving detection accuracy over time. The proposed system supports accurate real-time detection, providing a more intelligent and proactive defense against fraudulent activities. This approach enhances the security of UPI transactions, reduces financial losses, and strengthens user trust in digital financial services."
Disclaimer: Curated by HT Syndication.
