Real-Time Preemptive Fraud Detection Using Adaptive Agentic AI for Financial Transaction Risk Intelligence
Abstract
The sudden change of digital financial services has revolutionized the financial transactions, made them complicated, fast and large volume making it so challenging to the traditional financial fraud detection paradigms, which relies on predetermined patterns and a sluggish process. A Real-Time Preemptive Fraud Detection Framework is proposed in this study based on the Adaptive Agentic Artificial Intelligence (RPAFAI) to determine the intelligent financial transactions risk. The suggested system combines real-time transaction information, behavior categorization, situational risk assessment, dynamic machine learning, and self-sufficing AI programs to detect possible fraudulent actions prior to the conclusion of the transaction. The framework is further subdivided into six key levels, namely: (1) Transaction Data Ingestion Layer that constantly gathers transactional and contextual data; (2) Feature and Behavioral Intelligence Layer on which time and transactional-based requirements are temporally processed along with user/behavioral requirements, which are provisioned into future detection results; (3) Adaptive Agentic AI Layer that temporarily processes transactional capabilities in which the special AI agent gathers and an incorporated output that is translated into the future detection results; (4) Real-Time Risk Intelligence Layer where time and transactional-based requirements are processed continuously, alongside user/behavioral requirements, which are incorporated into future detection results; (5) Preemptive Decision and Response Layer that continually incorporates visible results into future detection results; and (6) Feedback and Continuous Learning Layer that constantly integrates results of known outcomes into future doubts. The framework is designed to minimize detection time, false positive and maximize its use to new trends of frauds and maximize real time financial risks knowledge. The proposed methodology provides an arena of active and independent prevention of frauds in the modern digital financial arena and ecosystems.
Article Information
Journal |
International Journal of Advanced Engineering Science and Information Technology (IJAESIT) |
|---|---|
Volume (Issue) |
Vol. 8 No. 5 (2025): International Journal of Advanced Engineering Science and Information Technology (IJAESIT) |
DOI |
|
Pages |
17324-17334 |
Published |
September 22, 2025 |
| Copyright | |
Open Access |
This work is licensed under a Creative Commons Attribution 4.0 International License. |
How to Cite |
Manas Ranjan Panda, PhD (2025). Real-Time Preemptive Fraud Detection Using Adaptive Agentic AI for Financial Transaction Risk Intelligence. International Journal of Advanced Engineering Science and Information Technology (IJAESIT) , Vol. 8 No. 5 (2025): International Journal of Advanced Engineering Science and Information Technology (IJAESIT) , pp. 17324-17334. https://doi.org/10.15662/IJAESIT.2025.0805016 |
References
[2] Y. Liu et al., “Improving fraud detection via hierarchical attention-based graph neural network,” Journal of Information Security and Applications, 2023.
[3] C. Zhao et al., “Advancing financial fraud detection: Self-attention generative adversarial networks for precise and effective identification,” Finance Research Letters, 2024.
[4] A. A. Amponsah et al., “A novel fraud detection and prevention method for healthcare claim processing using machine learning and blockchain technology,” Decision Analytics Journal, 2022.
[5] A. Ali et al., “Financial fraud detection based on machine learning: A systematic literature review,” Applied Sciences, 2022.
[6] Y. Dou et al., “Enhancing graph neural network-based fraud detectors against camouflaged fraudsters,” 2020.
[7] Y. Ding, Q. Yao, H. Zhao, and T. Zhang, “DiffMG: Differentiable meta graph search for heterogeneous graph neural networks,” 2021.
[8] Y. Fang et al., “Metagraph-based learning on heterogeneous graphs,” IEEE Transactions on Knowledge and Data Engineering, 2019.
[9] J. Zhou et al., “Graph neural networks: A review of methods and applications,” AI Open, 2020.
[10] T. Elsken, J.-H. Metzen, and F. Hutter, “Neural architecture search: A survey,” Journal of Machine Learning Research, vol. 20, pp. 1–21, 2019.
[11] S. Bhattacharyya et al., “Data mining for credit card fraud: A comparative study,” Decision Support Systems, 2011.
[12] K. G. Al-Hashedi and P. Magalingam, “Financial fraud detection applying data mining techniques: A comprehensive review from 2009 to 2019,” Computer Science Review, vol. 40, Art. no. 100402, 2021.
[13] W. Hilal, S. A. Gadsden, and J. Yawney, “Financial fraud: A review of anomaly detection techniques and recent advances,” Expert Systems with Applications, vol. 193, Art. no. 116429, 2022.
[14] M. Ali et al., “Financial Fraud Detection Based on Machine Learning: A Systematic Literature Review,” Applied Sciences, vol. 12, no. 19, Art. no. 9637, 2022.
[15] L. H. Aros et al., “Financial fraud detection through the application of machine learning techniques: A literature review,” Humanities and Social Sciences Communications, vol. 11, Art. no. 1130, 2024.