Intelligent Decision Support Driven by AI Agents in Financial Operations
DOI:
https://doi.org/10.54097/84jgz328Keywords:
Artificial intelligence, Financial operations, Multi-agent systems, Decision support, Algorithmic trading, Risk managementAbstract
Artificial intelligence is now used in all parts of a typical company and has changed the form of business. Systematically study the new model of intelligent decision-support systems driven by autonomous, multi-agent AI frameworks in this paper. In the past, because of old, error-prone rule-based computing methods, complex financial risk management and long-term capital allocation were relatively constrained. However, with the emergence of powerful large language models and high-end reinforcement learning algorithms, dynamic and constantly improving AI agents are now being deployed. These intelligent agents cooperate and discuss actively to process large volumes of unstructured market data in sequence, thereby producing highly optimised and perfectly rational financial strategies. The above research indicates that, at present, most models of individual prediction are disconnected from larger-scale, multi-agent automated trading and credit risk systems. In addition, this paper will also investigate how to build an explainable and trustworthy AI system that meets the high standards for international financial regulations. Based on the present study of multi-agent reinforcement learning for algorithmic trading and dynamic risk control, this paper puts forward an all-encompassing system to redesign corporate financial decisions in light of the increasing complexity of the global economy.
Downloads
References
[1] Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.
[2] Healy, P. M., & Palepu, K. G. (2001). Information asymmetry, corporate disclosure, and the capital markets: A review of the empirical disclosure literature. Journal of Accounting and Economics, 31(1-3), 405-440. https://doi.org/10.1016/S0165-4101(01)00018-0 DOI: https://doi.org/10.1016/S0165-4101(01)00018-0
[3] Leuz, C., & Wysocki, P. D. (2016). The economics of disclosure and financial reporting regulation: Evidence and suggestions for future research. Journal of Accounting Research, 54(2), 525-622.
https://doi.org/10.1111/1475-679X.12115 DOI: https://doi.org/10.1111/1475-679X.12115
[4] Fischer, T. G. (2018). Reinforcement learning in financial markets: A survey. FAU Discussion Papers in Economics, 12, 1-35.
[5] Liu, X. Y., Yang, H., Chen, Q., Zhang, R., Yang, L., Xiao, B., & Wang, C. D. (2021). FinRL: Deep reinforcement learning framework to automate trading in quantitative finance. In Proceedings of the Second ACM International Conference on AI in Finance (pp. 1-9). ACM. DOI: https://doi.org/10.1145/3490354.3494366
https://doi.org/10.1145/3490354.3490373
[6] Misheva, B. H., Osterrieder, J., Hirsa, A., Kulkarni, O., & Lin, S. F. (2021). Explainable AI in credit risk management. arXiv, arXiv:2103.00949. https://doi.org/10.48550/arXiv.2103.00949
[7] Fritz-Morgenthal, S., Hein, B., & Papenbrock, J. (2022). Financial risk management and explainable, trustworthy, responsible AI. Frontiers in Artificial Intelligence, 5, Article 779799. https://doi.org/10.3389/frai.2022.779799 DOI: https://doi.org/10.3389/frai.2022.779799
[8] Giudici, P., Centurelli, M., & Turchetta, S. (2024). Artificial intelligence risk measurement. Expert Systems with Applications, 235, Article 121220.
https://doi.org/10.1016/j.eswa.2023.121220 DOI: https://doi.org/10.1016/j.eswa.2023.121220
[9] Vyas, A. (2025). Revolutionizing risk: The role of artificial intelligence in financial risk management, forecasting, and global implementation. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5012345 DOI: https://doi.org/10.2139/ssrn.5224657
[10] Yarmohammadtoosky, S. (2025). Enhancing credit path planning with LLM-based multi-agent systems [Doctoral dissertation, Kennesaw State University].
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Computing and Electronic Information Management
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
