END-TO-END AI SOLUTION FOR UPI FRAUD MONITORING

Abstract

With the rapid adoption of Unified Payments Interface (UPI) for digital transactions, the risk of fraudulent activities has also increased significantly. To address this challenge, we propose a novel approach to detect UPI fraud by analyzing transaction details such as the bank book name, transaction ID, and transaction amount. Our method employs three machine learning algorithms: Random Forest, K-Nearest Neighbors (KNN), and Decision Tree. The system operates by processing provided transaction details to classify the transaction outcome as either "Transaction Failed: Incorrect Details Entered" or "Transaction Successful: Details Verified and Processed." Experimental evaluation suggests that these algorithms effectively distinguish between genuine and fraudulent transactions, demonstrating high accuracy and potential for integration into real-world financial systems to provide users with an additional layer of protection against unauthorized activities.