MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641112144 A) filed by Mlr Institute Of Technology; and Marri Laxman Reddy Institute Of Technology And Management on September 18, 2026, for Fraud Guard Ai: Real-Time Transaction Fraud Detection Using Ensemble Machine Learning.
Inventors include Mrs. A. Nirisha; Mr. Y. Chandra Vardhan; Ms. T. Arshitha; and Mr. Ch. Vishnu Varshith.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: With the rapid growth of digital banking, online transactions, and cashless payment systems, the risk of financial fraud has increased significantly, creating major challenges for banks, financial institutions, and customers. Traditional fraud monitoring approaches that depend heavily on manual inspection are increasingly ineffective because of the large volume, speed, and complexity of modern financial transactions. This invention presents Fraud Guard AI, a machine learning based fraud detection tool designed to identify potentially fraudulent credit card transactions accurately and efficiently. The system uses the widely recognized Kaggle credit card fraud dataset as the primary source for model development and evaluation. A major challenge associated with this dataset is its extreme class imbalance, where legitimate transactions substantially outnumber fraudulent transactions. To address this issue and improve the model’s ability to learn patterns associated with fraud, the Synthetic Minority Over-sampling Technique (SMOTE) is applied to generate representative synthetic examples of the minority fraud class. 5 Claims & 1 Figure.
Disclaimer: Curated by HT Syndication.
