Authors : Hemant Sharma; Kunal Sharma; Rahul Kumar

Volume/Issue : Volume 10 - 2025, Issue 6 - June

Google Scholar : https://tinyurl.com/5aybzrha

DOI : https://doi.org/10.38124/ijisrt/25jun328

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The rapid adoption of digital payments, particularly through the Unified Payments Interface (UPI), has led to a corresponding increase in the risk of fraud. To address this growing concern, this project introduces an intelligent, real-time fraud detection system designed specifically for UPI networks. Thissystem integrates rule-based logic, behavioural analytics, and supervised machine learning to effectively detect and prevent fraudulent transactions. It evaluates a wide range of transaction parameters—including amount, frequency, geolocation, device characteristics, and user behaviour—to establish a comprehensive fraud defence mechanism. Leveraging historical transaction data, the system uses supervised learning to identify anomalous patterns indicative of fraud. Its real-time processing capability allows it to flag suspicious transactions instantaneously, while its adaptive learning mechanism ensures it evolves in response to new types of fraudulent activity.  Key Features: • Multi-Factor Authentication (MFA): Enhances security by verifying user identity through multiple authentication layers. • Real-Time Pattern Analysis: Continuously monitors transaction activity to detect deviations from normal behaviour. • Behavioural Biometrics: Analyses user interactions such as typing speed or swipe patterns to identify potential account misuse. • Location-Based Verification: Validatestransaction origin using geolocation data to detect inconsistencies. • Dynamic Risk Scoring: Assigns a real-time risk score to each transaction by aggregating multiple behavioural and contextual signals. • Automated Alerts: Instantly notifies users or relevant authorities upon detection of potentially fraudulent transactions. This layered and adaptive approach ensures that the system not only detects fraud with high accuracy but also remains resilient against emerging fraud techniques, making it a robust solution for securing UPI-based digital payments.

References :

1. E. Aleskerov, B. Freisleben, and B. Rao, "CARDWATCH: A neural network-based database mining system for credit card fraud detection," Conference Proceedings, pp. 220–226, IEEE, Piscataway, NJ, 1997.
2. M. Sahin, Understanding Telephony Fraud as an Essential Step to Better Fight It [Thesis], École Doctorale Informatique, Télécommunication et Électronique, Paris, 2017.
3. A. Abdallah, M. A. Maarof, and A. Zainal, "Fraud detection system: A survey," Journal of Network and Computer Applications, vol. 68, pp. 90–113, 2016.
4. P. P. Andrews and M. B. Peterson (eds.), Criminal Intelligence Analysis, Palmer Enterprises, Loomis, CA, 1990.
5. M. Artís, M. Ayuso, and M. Guillén, "Modeling different types of automobile insurance fraud behavior in the Spanish market," Insurance: Mathematics and Economics, vol. 24, pp. 67– 81, 1999.
6. M. I. Barao and J. A. Tawn, "Extremal analysis of short series with outliers: Sea-levels and athletics records," Applied Statistics, vol. 48, pp. 469–487, 1999.
7. G. Blunt and D. J. Hand, The UK Credit Card Market, Technical Report, Dept. of Mathematics, Imperial College, London, 2000.
8. R. J. Bolton and D. J. Hand, "Unsupervised profiling methods for fraud detection," in Proc. Credit Scoring and Credit Control 7, Edinburgh, UK, 5–7 Sept. 2001.
9. C. Phua, V. Lee, K. Smith, and R. Gayler, "A comprehensive survey of data mining-based fraud detection research," 2010. [Online]. Available:https://doi.org/10.48550/arXiv.1009.6119
10. S. L. Summers and J. T. Sweeney, "Fraudulently misstated financial statements and insider trading: An empirical analysis," The Accounting Review, vol. 73, no. 1, pp. 131–146, 1998. [Online]. Available: https://www.jstor.org/stable/248345
11. P. L. Brockett, X. Xia, and R. A. Derrig, "Using Kohonen’s self-organizing feature map to
12. unveil automobile bodily injury claims fraud," Journal of Risk and Insurance, vol. 65, pp. 245– 274, 1998.
13. A. V. Sambra et al., "Solid: A platform for decentralized social applications based on linked data," 2016.
14. R. A. Becker, C. Volinsky, and A. R. Wilks, "Fraud Detect Telecommunications,"
15. Telecommunications, vol. 52, no. 1, pp. 20–33, 2010.
16. J. R. Dorronsoro, F. Ginel, C. Sanchez, and C. Santa Cruz, "Neural fraud detection in credit card operations," IEEE Transactions on Neural Networks, vol. 8, pp. 827–834, 1997.