EVALUATING MACHINE LEARNING ALGORITHMS FOR EFFECTIVE UPI FRAUD DETECTION: A COMPARATIVE ANALYSIS

Abstract: In 2021, the emergence of digital payment platforms, especially Unified Payments Interface (UPI), has resulted in a surge in cyber security risks and deceptive activities. As more users adopt UPI for their transactions, the risk of cyber frauds has become a significant concern. Protecting users from potential financial losses due to these threats has become imperative, necessitating the development of advanced security measures. This project aims to build a robust fraud detection system for UPI transactions using machine learning techniques. By analyzing transaction patterns and identifying anomalies, the system seeks to make UPI transactions more secure. The primary goal is to limit the losses for users in case of cyber frauds, ensuring a safer and more reliable digital payment experience.

Keywords: Machine Learning, UPI, Fraud, Random Forest, SVM, Decision Tree Regressor