MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641078369 A) filed by Cmr Engineering College, Kandlakoyav, Medchal Road, Hyderabad, Medchal Malkajgiri, Telangana-, India. on June 25, 2026, for Explainable Artificial Intelligence System For Real-Time Financial Fraud Detection.
Inventors include Dr. Laxmaiah Mettu, Professor, Computer Science And Engineering Data Science, Cmr Engineering College, Kandlakoya; Mr. S Jayavanth Rao, Assistant Professor, Computer Science And Engineering Data Science, Cmr Engineering College, Kandlakoya, Hydeabad-; Mr. R. Charkravarthi, Assistant Professor, Computer Science; Dr. Asha Shiny X S, Associate Professor, Computer Science And; Mr. V Kirankumar, Assistant Professor, Computer Science And; Mr. N. Raj Kumar, Assistant Professor, Computer Science And; and Mr. P. Goverdhan, Asst. Professor, Electronics And Communication Engineering, Cmr Engineering College, Kandlakoya, Hydeabad-.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: The present invention discloses an Explainable Artificial Intelligence System for Real-Time Financial Fraud Detection designed to detect fraudulent financial transactions while providing transparent and interpretable decision-making. The system integrates artificial intelligence, machine learning, and explainable AI techniques to enhance financial security and regulatory compliance. Transaction data collected from banking systems, payment gateways, digital wallets, and e-commerce platforms undergo preprocessing operations including cleaning, normalization, feature extraction, and anomaly filtering. Machine learning algorithms including Random Forest, XGBoost, Support Vector Machine (SVM), Deep Neural Networks (DNN), and Logistic Regression are employed to analyze transaction patterns, calculate fraud risk scores, and identify suspicious activities in real time. To improve transparency and trust, the framework incorporates explainability techniques such as SHAP, LIME, and feature importance analysis, enabling users and financial institutions to understand the reasoning behind fraud predictions. The system generates real-time alerts, transaction blocking notifications, and security reports to assist in immediate fraud prevention. Furthermore, cloud and edge computing architectures enable scalable deployment and low-latency processing across distributed financial environments. The proposed invention significantly improves fraud detection accuracy, reduces financial losses, enhances customer trust, and supports compliance with regulatory requirements. The system is applicable to banks, financial institutions, insurance companies, payment gateways, e-commerce platforms, and digital financial ecosystems, thereby providing a secure, transparent, and intelligent solution for modern financial fraud detection and risk management.
Disclaimer: Curated by HT Syndication.
