Intellectual Property India Publishes Patent Application for 'Hybrid Ensemble Learning System For Credit Card Fraud Detection' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122120 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'hybrid ensemble learning system for credit card fraud detection.'

Inventor(s) include Dr. Swetha. N. G.; Dr. Mugelan RK; and V Pranav.

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 hybrid ensemble learning system for credit card fraud detection. The system includes a data preprocessing module for processing financial transaction data, a class balancing module addressing class imbalance by generating synthetic samples for fraudulent transactions, diverse machine learning models including tree-based ensemble models and neural network-based models trained on balanced data, an ensemble combination module combining predictions to generate fraud detection predictions, and an evaluation module assessing performance. Tree-based models include XGBoost, LightGBM, and AdaBoost classifiers, while the neural network model includes a TabNet classifier with sequential attention mechanisms for tabular data processing. The class balancing module applies Synthetic Minority Over-sampling Technique, and the ensemble combination module uses soft voting that averages probability predictions from the diverse models."

Disclaimer: Curated by HT Syndication.