Volume 2 Issue 1 | 2025 | View PDF
Paper Id:IJMSM-V2I1P108
doi: 10.71141/30485037/V2I1P108

Enhancing UPI Fraud Detection: A Machine Learning Approach Using Stacked Generalization

Vitthal B Kamble, Krushna Pisal, Pranav Vaidya, Sahil Gaikwad

Citation:
Vitthal B Kamble, Krushna Pisal, Pranav Vaidya, Sahil Gaikwad, "Enhancing UPI Fraud Detection: A Machine Learning Approach Using Stacked Generalization" International Journal of Multidisciplinary on Science and Management, Vol. 2, No. 1, pp. 69-83, 2025.

Abstract:
The increasing prevalence of digital payments has led to a corresponding rise in fraudulent activities, necessitating robust detection mechanisms. Unified Payments Interface (UPI), a groundbreaking platform enabling instant financial transactions, has revolutionized the digital payment landscape but has also become a target for sophisticated fraud. This study presents an innovative fraud detection framework utilizing advanced machine learning techniques, behavioural analytics, and network-based anomaly detection. By analysing a heterogeneous dataset comprising authentic and fraudulent transactions, critical features such as transaction amount, timestamps, payer/payee details, and location information are engineered to enhance the model's performance. Time-sensitive and behavioural patterns are prioritized to identify anomalies effectively. The proposed system integrates both feature-based and network-based anomaly detection, leveraging the interaction between entities and their attributes to uncover hidden patterns associated with fraud. Real-time monitoring and alert mechanisms ensure immediate intervention, thereby safeguarding user trust and financial assets. Experimental results demonstrate the system's superior accuracy and adaptability compared to traditional methods, significantly reducing financial losses and enhancing the security of UPI transactions. This multi-faceted approach addresses diverse fraud scenarios, from transaction manipulation to money laundering, establishing a new benchmark in digital payment security.

Keywords: UPI, Fraud Detection, Machine Learning, Anomaly Detection, Behavioural Analytics, Network Analysis, Financial Security.

References:
1. Unified Payments Interface (UPI), National Payments Corporation of India, 2023. Online: https://www.npci.org.in/what-we-do/upi/product-overview
2. A. Singh, R. Gupta, and P. Sharma, “Challenges and Opportunities in UPI Fraud Detection,” International Journal of Financial Technologies, vol. 4, no. 3, pp. 45-58, 2022.
3. N. Aggarwal, and V. Kumar, “Limitations of Rule-Based Fraud Detection Systems in Digital Payments,” Journal of Financial Security, vol. 9, no. 2, pp. 101-115, 2021.
4. X. Zhang, Y. Wang, and L. Chen, “Machine Learning Techniques for Fraud Detection in Financial Transactions,” IEEE Transactions on Computational Intelligence, vol. 7, no. 6, pp. 1300-1315, 2020.
5. David H. Wolpert, “Stacked Generalization,” Neural Networks, vol. 5, no. 2, pp. 241-259, 1992.
6. Leo Breiman, “Random Forests,” Machine Learning, vol. 45, pp. 5-32, 2001.
7. Corinna Cortes, and Vladimir Vapnik, “Support-Vector Networks,” Machine Learning, vol. 20, pp. 273-297, 1995.
8. R. Ghosh, M. Das, and S. Roy, “Behavioral Analytics in Fraud Detection: A Study on Transaction Data,” Expert Systems with Applications, vol. 174, 2021.
9. S. Hashemi, M. Turaba, and R. Khosrowabadi, "Integrating Machine Learning Techniques for Fraud Detection in Digital Payment Systems," Journal of Financial Security, vol. 10, no. 2, pp. 105-120, 2022.
10. M. Naga Raju et al., “Detection of Fraudulent Activities in Unified Payments Interface using Machine Learning - LSTM Networks,” 7th International Conference on Circuit Power and Computing Technologies (ICCPCT), Kollam, India, pp. 769-774, 2024.
11. G.R. Charan, and K.D. Thilak, “Detection of Phishing Link and QR Code of UPI Transaction using Machine Learning,” 3rd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Bengaluru, India, pp. 658-663, 2023.
12. Rupa Rani, Adnan Alam, and Abdul Javed, “Secure UPI: Machine Learning-Driven Fraud Detection System for UPI Transactions,” 2nd International Conference on Disruptive Technologies (ICDT), Greater Noida, India, pp. 924-928, 2024.
13. Vaishali Gupta et al., “UPI Based Financial Fraud Detection Using Deep Learning Approach,” International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET), Indore, India, pp. 1-6, 2024.
14. Abdul Rehman Khalid et al., “Enhancing Credit Card Fraud Detection: An Ensemble Machine Learning Approach,” Big Data and Cognitive Computing, vol. 8, no. 1, pp. 1-27, 2024.
15. Omkar Dabade et al., “Developing an Intelligent Credit Card Fraud Detection System with Machine Learning,” Journal of Artificial Intelligence, Machine Learning and Neural Network, vol. 2, no. 1, pp. 45-53, 2022.
16. Vitthal B. Kamble, and Dr. Nilesh J. Uke, Ethical Hacking, San International, 2024.
17. Sunil S Mhamane, and L.M.R.J Lobo, “Internet Banking Fraud Detection Using HMM,” Third International Conference on Computing, Communication and Networking Technologies (ICCCNT'12), Coimbatore, India, pp. 1-4, 2012.
18. Akash Pushkar, Fraud Detection Algorithms Using Machine Learning, Intellipaat, 2024. Online: https://intellipaat.com/blog/fraud-detection-machine-learning-algorithms/
19. Dongxu Huang et al., “CoDetect: Financial Fraud Detection with Anomaly Feature Detection,” IEEE Access, vol. 6, pp. 19161-19174, 2018.
20. Scikit-learn: Machine Learning in Python. Online: https://scikit-learn.org/stable/
21. Scott Menard, Applied Logistic Regression Analysis, SAGE Publications, pp. 1-111, 2002.
22. David W. Hosmer, and Stanley Lemeshow, Applied Logistic Regression, Wiley, pp. 1-373, 2000.
23. M. Mollah, and M.S. Islam, “Logistic regression in fraud detection,” Journal of Financial Engineering, vol. 12, no. 1, pp. 67-81, 2021.
24. Thomas G. Dietterich, “Ensemble Methods in Machine Learning,” Multiple Classifier Systems, pp. 1-15, 2000.
25. X. Liu, and S. Yang, “A Comprehensive Study of Random Forest in Machine Learning,” International Journal of Machine Learning and Computing, vol. 8, no. 6, pp. 674-683, 2018.
26. A. Rajput, and R. Gupta, “Application of Random Forest for Fraud Detection in Financial Transactions,” Journal of Data Science and Analytics, vol. 15, no. 3, pp. 230-246, 2020.
27. Vladimir N. Vapnik, Statistical Learning Theory, John Wiley & Sons, 1998.
28. Chih-Chung Chang, and Chih-Jen Lin, “LIBSVM: A Library for Support Vector Machines,” ACM Transactions on Intelligent Systems and Technology, vol. 2, no. 3, pp. 1-27, 2011.
29. M. Bennasar, and M. Barrenechea, “Using SVM for Fraud Detection in Digital Payment Systems,” Expert Systems with Applications, vol. 45, pp. 128-134, 2019.
30. J.R. Quinlan, “Induction of Decision Trees,” Machine Learning, vol. 1, pp. 81-106, 1986.
31. Y. Liu, and W. Liu, “Understanding Decision Trees and their Applications in Fraud Detection,” Journal of Computing and Security, vol. 35, no. 4, pp. 1421-1435, 2020.
32. M. O’Neill, and R. Smith, “Using Decision Trees for Fraud Detection in Financial Transactions,” Financial Technology Review, vol. 22, no. 2, pp. 33-48, 2021.
33. F.T. Liu, K.M. Ting, and Z.H. Zhou, “Isolation Forest,” Eighth IEEE International Conference on Data Mining, Pisa, Italy, pp. 413-422, 2008.
34. J. Wang, and Q. Li, “Anomaly Detection in Financial Transactions Using Isolation Forest,” Journal of Applied Data Science, vol. 6, no. 2, pp. 120-133, 2018.
35. Y. Liu, and M. Fang, “Using PCA for Fraud Detection in Large Financial Datasets,” Journal of Financial Technology, vol. 5, no. 1, pp. 99-115, 2020.
36. X. Xia, and J. Zhang, “Unsupervised Anomaly Detection for Fraud Detection,” Journal of Machine Learning in Finance, vol. 7, no. 1, pp. 45-61, 2019.
37. Y. Zhang, and Z. Xu, “Anomaly Detection Using Isolation Forest for Fraud Detection in UPI Transactions,” Financial Technology and Innovation, vol. 17, no. 3, pp. 90-106, 2021.
38. I.T. Jolliffe, Principal Component Analysis, Springer Series in Statistics, 2002.
39. Jonathon Shlens, “A Tutorial on Principal Component Analysis,” arXiv, pp. 1-12, 2014.
40. H. Zhao, and X. Wang, “Dimensionality Reduction for Fraud Detection using PCA,” Journal of Data Science, vol. 10, no. 3, pp. 218-229, 2021.
41. Support Vector Machine Algorithm, Online: https://www.javatpoint.com
42. Random Forest Fraud Detection.
43. Vitthal B. Kamble et al., “Machine Learning in Fake News Detection and Social Innovation: Navigating Truth in the Digital Age,” Exploring Psychology, Social Innovation and Advanced Applications of Machine Learning, pp. 87-108, 2025.