MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641105949 A) filed by Sri Eshwar College Of Engineering on September 02, 2026, for Franchise-Driven E-Commerce Marketplace: Connecting Consumers And Brand Proprietors.
Inventor includes Mr. M. Mohanraj.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: The rapid growth of digital financial transactions has brought increasing challenges in detecting fraud within these complex systems. Traditional fraud detection methods often fall short when faced with the sophisticated and interconnected tactics used by modern fraudsters. This project investigates the potential of Graph Neural Networks (GNNs) as a more effective solution. By modeling users, accounts, and transactions as nodes, and their interactions as edges, GNNs can uncover hidden relationships and behavioral patterns that conventional models may fail to detect. We collected a large set of transactional data from financial institutions, carefully preprocessed it to ensure accuracy, and then trained a GNN model to distinguish between legitimate and fraudulent activity. The model’s performance was evaluated using standard metrics such as accuracy, precision, recall, and F1 score. The results show that GNNs not only improve detection rates but are especially effective at identifying complex, coordinated fraud schemes while reducing false alarms. This study highlights the strong potential of GNNs to strengthen fraud detection systems and enhance trust in digital financial services. Looking ahead, we see opportunities to extend this work into real-time fraud detection and to combine GNNs with other machine learning techniques for even greater effectiveness as fraud tactics continue to evolve.
Disclaimer: Curated by HT Syndication.
