MUMBAI, India, June 16 -- Intellectual Property India has published a patent application (202611054043 A) filed by Mr. Vishwas Tayal; Mr. Sumit Priyadarshi; Mr. Vivek Sundriyal; and Ms. Shalu, Ghaziabad, Uttar Pradesh, on April 28, for 'credit card fraud detection using machine learning.'
Inventor(s) include Mr. Vishwas Tayal; Mr. Sumit Priyadarshi; Mr. Vivek Sundriyal; and Ms. Shalu.
The application for the patent was published on June 5, under issue no. 23/2026.
According to the abstract released by the Intellectual Property India: "This invention presents an intelligent and scalable credit card fraud detection system leveraging advanced machine learning techniques including Random Forest, XGBoost, and anomaly detection models. The system processes high-volume transactional data in real time and employs a hybrid architecture combining supervised and unsupervised learning for enhanced detection capability. The proposed framework incorporates robust data preprocessing, Principal Component Analysis (PCA) for dimensionality reduction, and advanced feature engineering techniques to extract behavioral and transactional patterns such as spending frequency, velocity, and geographical deviations. To address the issue of highly imbalanced datasets, the system integrates SMOTE and cost-sensitive learning mechanisms. The model achieves high precision, recall, and F1-score while significantly reducing false positives through ensemble learning and threshold optimization. Additionally, a continuous feedback loop enables adaptive learning to handle ev."
Disclaimer: Curated by HT Syndication.
