Authors : Dr. D. Jaya Kumari; Gurram Tejaswi; Nekkanti Durga Sri Jahnavi; Korapati Anusha; Kotakonda Naga Kathyayani; Areti Divya Sri; Medapati Sharmila

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/3usw7k28

Scribd : https://tinyurl.com/4zc2rxf4

DOI : https://doi.org/10.38124/ijisrt/25apr830

Google Scholar

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

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : A significant step in safeguarding India's digital economy against cyber threats is the implementation of AI-driven fraud detection systems in Unified Payments Interface (UPI) transactions. Real-time transaction analysis is made possible by AI technologies, especially machine learning and deep learning, which aid in identifying anomalous patterns that might point to fraud. In 2023, there will be over 100 billion UPI transactions, increasing the need for sophisticated fraud detection techniques. These systems utilize anomaly detection, behavioral biometrics, and network analysis to monitor user interactions and transaction patterns. AI analyzes keystroke dynamics, mouse movements, and transaction history to differentiate legitimate users from fraudsters. Research shows that Generative AI (GenAI) enhances fraud detection accuracy by continuously assessing behavioral patterns, enabling swift identification of suspicious activities. Additionally, combining AI models like Random Forest, Naïve Bayes, and Support Vector Machines (SVMs) improves detection efficiency while reducing false positives. The flexibility of these AI models is crucial for combating new fraud methods, including deepfake scams and synthetic identity fraud. Additionally, initiatives like the Reserve Bank of India's MuleHunter.ai are instrumental in identifying mule accounts involved in illegal transactions and facilitating real-time fraud monitoring among financial institutions. This joint effort strengthens the security infrastructure while ensuring adherence to regulatory requirements for anti-money laundering and counter-terrorism financing. The growing use of AI-driven solutions to identify UPI fraud signifies a notable change in how financial institutions address security issues in an increasingly digital economy. With 72% of financial institutions in India currently employing or considering Generative AI (GenAI)-based technology for fraud prevention, the sector is experiencing a significant transformation that emphasizes the importance of security alongside user experience. As these technologies evolve, they will be vital in fostering consumer confidence and preserving the integrity of India's digital payment landscape in the face of changing cyber threats.

Keywords : NLP, UPI, Digital Platforms.

References :

1. Jagadeesan, S., K. S. Arjun, G. Dhanika, G. Karthikeyan, and K. Deepika. "UPI fraud detection using machine learning." In Challenges in Information, Communication and Computing Technology, pp. 755-760. CRC Press, 2025.
2. Bello, Oluwabusayo Adijat, and Komolafe Olufemi. "Artificial intelligence in fraud prevention: Exploring techniques and applications challenges and opportunities." Computer science & IT research journal 5, no. 6 (2024): 1505-1520.
3. Gupta, Yash, Nitesh Saxena, and Krishan Kumar. "UPI Fraud Detection Using Machine Learning."
4. Sindhu, Jallapuram, and Ms Vijaya Sree Swarupa. "UPI FRAUD DETECTION USING MACHINE LEARNING ALGORITHMS." International Journal of Engineering Research and Science & Technology 20, no. 4 (2024): 57-67.
5. Dhanwani, D. C., Aniruddh Tonpewar, Devashish Ikhar, Komal Ladole, and Suyog Mahant. "Online Fraud Detection System."
6. Edburg, B. Franklin, K. Umadevi, M. Vidya, and PM Ramesh Kumar. "Role of UPI Application Usage and Mitigation of Payment Transaction Frauds: An Empirical Study." MDIM JOURNAL OF MANAGEMENT REVIEW AND 7 (2024).
7. Rajakrishnan Manivel, Dr D., and J. S. Harsika. "USER’S BEHAVIOUR TOWARDS UPI TRANSACTIONS OF COMMERCIAL BANKS IN COIMBATORE CITY."
8. NAGARAJU, MELAM, Polavarapu Nagendra Babu, Venkata Sai Pavan Ravipati, and Velpula Chaitanya. "UPI fraud detection using convolutional neural networks (CNN)." (2024).
9. Soni, Sanskar, Shweta Kanojiya, Siddharth Yadav, Rajendra Arakh, and Richa Shukla. "Online Payment Fraud Detection System Using Convolution Neural Network."
10. Gupta, Pankaj. "Leveraging machine learning and artificial intelligence for fraud prevention." SSRG International Journal of Computer Science and Engineering 10, no. 5 (2023): 47-52.