• Vipul Zope
• Pritamsingh Ratra
• Ishaan Mattoo
• Dr. Saurabh Saoji

The rapid growth of digital payments through the Unified Payments Interface (UPI) in India has transformed the financial landscape, enabling over 1 billion transactions monthly and processing volumes exceeding ₹20 trillion INR annually [1]. However, this growth has created new opportunities for fraudsters, with reported fraud cases increasing by 32% year-over-year [2]. Traditional fraud detection methods struggle with the volume, velocity, and complexity of modern digital transactions. This paper presents a comprehensive study on detecting fraudulent UPI transactions using a 1D Convolutional Neural Network (CNN). Our approach leverages transactional data with carefully engineered features to train a deep learning model that can distinguish between legitimate and fraudulent transactions. The model demonstrates exceptional performance across various types of UPI fraud, including impersonating sellers, phishing, screen mirroring, OTP/PIN fraud, collection request fraud, and misleading UPI handles. The results show near-perfect classification metrics, with accuracy, precision, recall, and F1-score all reaching 1.00. The architecture's ability to learn temporal patterns in transaction data proves valuable for detecting sophisticated fraud techniques. This study successfully applies 1D CNN to UPI fraud detection, achieving near-perfect accuracy across multiple fraud types. The approach offers a robust solution for financial institutions to enhance their fraud detection capabilities in digital payment systems.

UPI Fraud Detection, 1D CNN, Digital Payments Security, Financial Fraud Prevention, Deep Learning, Transaction Pattern Analysis, Deep Learning Optimization

"Leveraging 1D Convolutional Neural Networks for Fraud Detection in Unified Payments Interface (UPI)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.e693-e705, March-2025, Available :http://www.jetir.org/papers/JETIR2503493.pdf

"Leveraging 1D Convolutional Neural Networks for Fraud Detection in Unified Payments Interface (UPI)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppe693-e705, March-2025, Available at : http://www.jetir.org/papers/JETIR2503493.pdf