Enhanced UPI Fraud Detection Using CNN: A Comparative Analysis with Machine Learning Models
Abstract
The Unified Payment Interface (UPI) has transformed the landscape of digital payments, significantly enhancing the pace of digitization. It has redefined the financial ecosystem by facilitating quicker, simpler, and more accessible cashless transactions for individuals across the nation. However, the increasing use of UPI has also made it a target for various fraudulent activities. Therefore, it is essential to detect fraudulent transactions in real-time by leveraging artificial intelligence techniques. Many machine learning algorithms are used to detect fraudulent transactions, but most of them rely heavily on historical transactional data to identify patterns and anomalies. While historical data provides valuable insights into past fraud patterns, it may not be sufficient to detect dynamic patterns in evolving fraudulent transactions. We propose a CNN-based fraud detection model that recognizes complex patterns in real-time transactional data. In this paper, we analyze the performance of machine learning algorithms and a CNN-based approach. Our results demonstrate that the CNN-based model outperforms traditional machine learning models in detecting UPI frauds.
How to Cite This Article
Sekuri Manju Bhargavi, Bandaru Kesava Ram (2025). Enhanced UPI Fraud Detection Using CNN: A Comparative Analysis with Machine Learning Models . International Journal of Multidisciplinary Research and Growth Evaluation (IJMRGE), 6(2), 452-455. DOI: https://doi.org/10.54660/IJMRGE.2025.6.2.452-455
References
- 1. Vadlamudi S, Sam J. Unified Payments Interface Preservingthe Data Privacyof Consumers. International Conferenceon Cyber Resilience(ICCR\, Dubai, United Arab Emirates.2022; p.16. doi:10.1109/ICCR56254.2022.10024689.
- 2. Dev H, Gupta R, Kumar D. Cashto Cashless: UPI's Impacton Spending Behavioramong Indian Users. Extended Abstractsofthe CHIConferenceon Human Factorsin Computing Systems(CHIEA'24\. Associationfor Computing Machinery, New York, NY, USA.2024; Article168, p.110. https://doi. org/10.1145/3613905.3651050.
- 3. Lakshmi KK, Gupta H, Ranjan J. UPI-Based Mobile Banking Applications Security Analysisand Enhancements. Amity International Conferenceon Artificial Intelligence(AICAI\, Dubai, United Arab Emirates.2019; p.16. doi:10.1109/AICAI.2019.8701396.
- 4. Kumar R, Kishore S, Lu H, Prakash A. Securityanalysisofunifiedpaymentsinterfaceandpaymentappsin India. Proceedingsofthe29th USENIXConferenceon Security Symposium(SEC'20\. USENIXAssociation, USA.2020; Article85, p.14991516.
- 5. Shree S, Pratap B, Saroy R, etal Digitalpaymentsandconsumerexperiencein India: asurvey-basedempiricalstudy. JBank Financ Technol.2021;5. https://doi. org/10.1007/s42786-020-00024-z.
- 6. Madwanna Y, Khadse M, Chandavarkar BR. Security Issuesof Unified Payments Interfaceand Challenges: Case Study.2nd International Conferenceon Secure Cyber Computingand Communications(ICSCCC\, Jalandhar, India.2021; p.1504. doi:10.1109/ICSCCC51823.2021.9478078.
- 7. Mothukuri NPHK, Rakesh A, Babu PY, Kiran U, BG, Hazarika BB. AComprehensive Studyof Different Security Featuresine Banking. Third International Conferenceon Artificial Intelligenceand Smart Energy(ICAIS\Coimbatore, India.2023; p.117781. doi:10.1109/ICAIS56108.2023.10073735.
- 8. Rani R, Alam A, Javed A. Secure UPI: Machine Learning-Driven Fraud Detection Systemfor UPITransactions.2nd International Conferenceon Disruptive Technologies(ICDT\, Greater Noida, India.2024; p.9248. doi:10.1109/ICDT61202.2024.10489682.
- 9. Mytnyk B, Tkachyk O, Shakhovska N, Fedushko S, Syerov Y. Applicationof Artificial Intelligencefor Fraudulent Banking Operations Recognition. Big Data Cogn Comput.2023;7:93. https://doi. org/10.3390/bdcc7020093.
- 10. Naikl SKL, Kiran A, Kumar VP, Mannam S, Kalyani Y, Silparaj M. Fraud Fighters-How AIand MLare Revolutionizing UPISecurity. International Conferenceon Science Technology Engineeringand Management(ICSTEM\, Coimbatore, India.2024; p.17. doi:10.1109/ICSTEM61137.2024.10560740.