• Mr.Sakshith A R
• Dr. Shashidhar Kini K

The UPI fraud detection system aims to develop a robust and efficient machine learning-based model for identifying fraudulent financial transactions in real-time. By leveraging advanced classification algorithms such as Random Forest, XGBoost, and LSTM, the system analyzes patterns in transaction data to accurately detect and flag anomalies that indicate potential fraud. The model learns user behavior over time, including transaction frequency, amount, location, and recipient patterns, to identify deviations from typical usage. It also considers temporal features and cross-account interactions to enhance predictive accuracy and reduce false positives. By integrating these diverse data features and optimizing model performance for rapid response, the objective is to create a reliable, scalable, and intelligent fraud detection framework. This system can be effectively deployed in banking and fintech environments, offering users and institutions real-time insights and protection against unauthorized activities, thus improving digital transaction security and trust.

UPI Transactions, Fraud Detection, Machine Learning, Random Forest, XGBoost, LSTM, Anomaly Detection, Real-Time Processing, Financial Security

"UPI FRAUD DETECTION USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.1036-1039, July-2025, Available :http://www.jetir.org/papers/JETIRGX06194.pdf

"UPI FRAUD DETECTION USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp1036-1039, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06194.pdf