Machine Learning Architectures for Real-Time Fraud Prevention in High-Velocity Financial Networks

Authors

  • Anuraag Mangari Neburi

Keywords:

Finance, Machine Learning, Velocity, Fraud, Architecture

Abstract

In the paper, it is suggested to implement a real-time architecture of a fraud detection system that can apply to the current digital payment systems. It is founded on supervised learning, graph neural networks, and anomaly detection and reinforcement learning to improve flexibility and accuracy. It is a multimodal system in which it is based on details of transactions, device patterns, behavior and account network sequences. The results of the experiment are more accurate and recollections than the traditional models with low latency that can be applied to the real time in finance. The architecture is also easy to adapt to the unexpected changes in the fraud trends such as account takeovers and mules networks. The proposed framework is a more rationalized, large-scale and explainable framework of fraud detection.

Downloads

Download data is not yet available.

References

Lu, M., Han, Z., Rao, S. X., Zhang, Z., Zhao, Y., Shan, Y., Raghunathan, R., Zhang, C., & Jiang, J. (2022). BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.13084

Tian, Y., Liu, G., Wang, J., & Zhou, M. (2023). Transaction fraud detection via an adaptive graph neural network. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2307.05633

Cui, Y., Han, X., Chen, J., Zhang, X., Yang, J., & Zhang, X. (2025). FRAUdGNN-RL: A Graph Neural network with reinforcement learning for adaptive financial fraud Detection. IEEE Open Journal of the Computer Society, 6, 426–437. https://doi.org/10.1109/ojcs.2025.3543450

Rahmati, M. (2025, March 29). Real-Time financial fraud detection using adaptive graph neural networks and federated learning. https://ijmada.com/index.php/ijmada/article/view/77

Singh, M. T., Prasad, R. K., Michael, G. R., Kaphungkui, N. K., & Singh, N. H. (2024). Heterogeneous Graph Auto-Encoder for CreditCard fraud detection. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.08121

Motie, S., & Raahemi, B. (2023). Financial fraud detection using graph neural networks: A systematic review. Expert Systems With Applications, 240, 122156. https://doi.org/10.1016/j.eswa.2023.122156

Yang, Y., Xu, C., & Tian, G. (2025). Lightweight financial fraud detection using a symmetrical GAN-CNN fusion architecture. Symmetry, 17(8), 1366. https://doi.org/10.3390/sym17081366

Vallarino, D. (2025). AI-Powered Fraud Detection in Financial Services: GNN, compliance challenges, and risk mitigation. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5170054

Wang, X., & Wang, Y. (2025). Real-time transaction flow analysis with graph neural networks for financial fraud detection. Journal of Computational Methods in Sciences and Engineering. https://doi.org/10.1177/14727978251385133

Polu, O. R., Chamarthi, B., Chowdhury, T., Ushmani, A., Kasralikar, P., Syed, A. A., Mishra, A., Anumula, S. K., Rajendran, R. N., Mohanty, M. R., & Prova, N. N. I. (2025). Graph Neural Networks for Fraud Detection: Modeling financial transaction networks at scale. In Advances in economics, business and management research/Advances in Economics, Business and Management Research (pp. 712–729). https://doi.org/10.2991/978-94-6463-872-1_45

Downloads

Published

11.12.2025

How to Cite

Anuraag Mangari Neburi. (2025). Machine Learning Architectures for Real-Time Fraud Prevention in High-Velocity Financial Networks . International Journal of Intelligent Systems and Applications in Engineering, 13(2s), 96–104. Retrieved from https://mail.ijisae.org/index.php/IJISAE/article/view/7965

Issue

Vol. 13 No. 2s (2025)

Section

Research Article

License

Copyright (c) 2025 Anuraag Mangari Neburi

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.