IJCOPE Journal

UGC Logo DOI / ISO Logo

International Journal of Creative and Open Research in Engineering and Management

A Peer-Reviewed, Open-Access International Journal Supporting Multidisciplinary Research, Digital Publishing Standards, DOI Registration, and Academic Indexing.
Journal Information
ISSN: 3108-1754 (Online)
Crossref DOI: Available
ISO Certification: 9001:2015
Publication Fee: 599/- INR
Compliance: UGC Journal Norms
License: CC BY 4.0
Peer Review: Double Blind
Volume 02, Issue 04

Published on: April 2026

MITIGATING CONCEPT DRIFT IN HIGH-VELOCITY UPI PAYMENTS: AN ADAPTIVE HYBRID DQN-XGBOOST FRAMEWORK

Anukriti Sharma Aishwarya G.

Dr. Hema M S

Department of Computer Science and Engineering

R.V. Institute of Technology and Management

Bengaluru India
DOI:https://doi.org/10.55041/ijcope.v2i4.955

Article Status

Plagiarism Passed Peer Reviewed Open Access

Available Documents

Download PDF Review Report

Abstract

As the use of Unified Payments Interface (UPI) has grown exponentially in the modern financial ecosystem, adaptive fraud detection systems capable of mitigating evolving attack strategies under strict latency constraints have become essential. Most conventional machine learning approaches rely primarily on static historical data and treat fraud detection as a static classification task, which limits their responsiveness to shifting behavioral patterns. This paper proposes a hybrid framework that redefines fraud identification as a sequential decision process by integrating Deep Q-Networks (DQN) with XGBoost. In our proposed architecture, XGBoost performs high-precision classification on structured transactional features in conjunction with a DQN component that dynamically refines detection policies through reinforcement learning. This design facilitates a novel decision process that enhances sensitivity to emerging fraud variants. Experimental results demonstrate 98.7% accuracy and 98.5% recall, with an average inference latency of 45 ms, confirming the framework’s scalability for high-volume UPI ecosystems.

Index Terms—Financial Fraud Detection, Deep Q-Networks (DQN), XGBoost, Concept Drift, Real-Time Security, UPI

How to Cite this Paper

Sharma, A. & G., A. (2026). Mitigating Concept Drift in High-Velocity UPI Payments: An Adaptive Hybrid DQN-XGBoost Framework. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(04). https://doi.org/10.55041/ijcope.v2i4.955

Sharma, Anukriti, and Aishwarya G.. "Mitigating Concept Drift in High-Velocity UPI Payments: An Adaptive Hybrid DQN-XGBoost Framework." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i4.955.

Sharma, Anukriti, and Aishwarya G.. "Mitigating Concept Drift in High-Velocity UPI Payments: An Adaptive Hybrid DQN-XGBoost Framework." International Journal of Creative and Open Research in Engineering and Management 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i4.955.

Search & Index

Google Scholar Crossref DOI ResearchGate

References


  • Lingareddy, D. Indoria, S. Deepika, G. George, M. K. Priya, andR, ”Enhancing digital payment security: UPI fraud detection with advanced machine learning algorithms,” in 2025 Global Conference in Emerging Technology (GINOTECH), 2025, pp. 1-7.



  • Chen and C. Guestrin, ”XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016,785-794.



  • Naga Raju, Y. Chandrasena Reddy, P. Nagendra Babu, V. S. P. Ravipati, and V. Chaitanya, ”Detection of fraudulent activities in unified payments interface using machine learning - LSTM networks,” in 2024 7th International Conference on Circuit Power and Computing Technologies (ICCPCT), 2024, vol. 1, pp. 769-774.

  • Mnih et al., ”Human-level control through deep reinforcement learn-ing,” Nature, vol. 518, no. 7540, pp. 529-533, Feb. 2015.

  • Gama, I. Zˇ liobaite˙, A. Bifet, M. Pechenizkiy, and A. Bouchachia, ”A survey on concept drift adaptation,” ACM Computing Surveys, vol. 46, no. 4, pp. 1-37, Apr. 2014.

  • Abdallah, M. A. Maarof, and A. Zainal, ”Fraud detection system: A survey,” Journal of Network and Computer Applications, vol. 68, pp. 90-113, Jun. 2016.

  • H. Trinity and N. Sharma, ”Unified payments interface (UPI): Fraud and prevention strategies,” in 2025 International Conference on Electronics, Computing, Communication and Control Technology (ICECCC), 2025, pp. 1-6.

  • Bardhan, R. Garay-Paravisini, G. Dorai, and L. Vanputte, ”Digital forensics analysis of a financial mobile application: Uncovering security and privacy implications,” in 2024 International Symposium on Net-works, Computers and Communications (ISNCC), 2024, pp. 1-8.

  • Kuriakose, P. B. Sajoy, and E. George, ”Modelling the consumer adoption intention towards unified payment interface (UPI): An extended UTAUT2 model with relative advantage, add-on services and promo-tional benefits,” in 2022 Interdisciplinary Research in Technology and Management (IRTM), 2022, pp. 1-7.

  • K. Lokesh Naikl, A. Kiran, V. P. Kumar, S. Mannam, Y. Kalyani, and M. Silparaj, ”Fraud fighters - How AI and ML are revolutionizing UPI security,” in 2024 International Conference on Science Technology Engineering and Management (ICSTEM), 2024, pp. 1-7.

Ethical Compliance & Review Process

  • •All submissions are screened under plagiarism detection.
  • •Review follows editorial policy.
  • •Authors retain copyright.
  • •Peer Review Type: Double-Blind Peer Review
  • •Published on: May 01 2026
CCBYNC

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.

View License
Back to Volume 02, Issue 04View All Issues Next Article

← Previous Article

Minimum Spanning Tree Based Network Design Using Prim’s and Kruskal’s Algorithms

Next Article →

Mitigating Security Threats in Smart Devices Through Artificial Intelligence
Scroll to Top