Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202045,
        author = {SAMEEN JALIB and Habib Adnan A},
        title = {AI-Based UPI Transaction Fraud Detection and Analysis Framework},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {5786-5791},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202045},
        abstract = {The increasing adoption of Unified Payments Interface (UPI) systems has significantly transformed digital transactions by providing fast, secure, and convenient payment services. However, the rapid growth of online payment platforms has also resulted in a rise in fraudulent activities such as phishing, identity theft, unauthorized access, and fake transaction requests. Traditional fraud detection approaches are often unable to identify newly emerging fraud patterns efficiently due to their static and rule-based nature. To overcome these limitations, this research proposes an AI-based fraud detection and analysis system for UPI transactions using machine learning techniques. The proposed framework analyses transaction behaviour, user activity, transaction frequency, device information, and location patterns to identify suspicious activities in real-time. The dataset is preprocessed using feature engineering and normalization techniques to improve model performance. A Random Forest classifier is implemented for fraud prediction because of its robustness, high accuracy, and capability to handle large transactional datasets. The model is evaluated using performance metrics such as accuracy, precision, recall, and F1-score. Experimental results demonstrate that the proposed system effectively identifies fraudulent transactions while minimizing false alerts. The developed framework enhances transaction security, improves trust in digital payment systems, and supports real-time fraud prevention mechanisms in modern UPI environments.},
        keywords = {UPI Fraud Detection; Machine Learning; Digital Payments; Classification Models; Real-Time Fraud Analysis; Transaction Monitoring; Behavioral Pattern Analysis; Cyber Security; Financial Fraud Prevention; Alert System.},
        month = {May},
        }