Hierarchical Multi-Agent Reinforcement Learning Framework with Cloud-Based Coordination for Scalable Regulatory Enforcement in Financial Systems
Raj Sonani
Published 2023-12-11
Keywords
- Multi-Agent Reinforcement Learning,
- cloud computing,
- financial law violations,
- transparency,
- regulatory enforcement
How to Cite
Copyright (c) 2023 Spectrum of Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
Abstract
A paramount interest in the gradual advancement of the entire stock market system has been not to enact live and efficient procedures to weed out common financial law violations and tame the lack of transparency among the main actors. On the other hand, this never solves the matter while the authority bodies for that regulation tend to be dysfunctional, underfinanced, and, because of those, rather unpredictable in their policies. This situation is not just unfair to traders; it is also a hindrance to market growth and innovation. Officials such as the SEC, FINRA, and CFTC are each established on their own turf that usually captures the interests and activities of other agencies, thereby leading to several problems such as the poor implementation of the policy in the case of high-frequency trading. It is more common in such cases that a few agencies, several of which may work independently, be engaged in the regulatory and supervisory process. This paper proposes a method to deal with it by means of a hierarchical MARL (multi-agent reinforcement learning) approach which is operated by the cloud coordinating system to develop the enforcement of various agencies. This plan's fundamental principle is the function of regulators' deployment to various segments of a cloud enabler, the ability to produce information in real-time, the facilitation of scalable computing tasks and sharing of authorities.
References
- G. Alhussein, M. Alkhodari, A. Khandoker, and L. J. Hadjileontiadis, "Emotional climate recognition in interactive conversational speech using deep learning," in 2022 IEEE International Conference on Digital Health (ICDH), 2022: IEEE, pp. 96-103.
- B. R. Chirra, "Enhancing Cybersecurity Resilience: Federated Learning-Driven Threat Intelligence for Adaptive Defense," International Journal of Machine Learning Research in Cybersecurity and Artificial Intelligence, vol. 11, no. 1, pp. 260-280, 2020.
- D. R. Chirra, "Deep Learning Techniques for Anomaly Detection in IoT Devices: Enhancing Security and Privacy," Revista de Inteligencia Artificial en Medicina, vol. 14, no. 1, pp. 529-552, 2023.
- R. G. Goriparthi, "Machine Learning in Smart Manufacturing: Enhancing Process Automation and Quality Control," International Journal of Machine Learning Research in Cybersecurity and Artificial Intelligence, vol. 11, no. 1, pp. 438-457, 2020.
- I. Naseer, "The efficacy of Deep Learning and Artificial Intelligence framework in enhancing Cybersecurity, Challenges and Future Prospects," Innovative Computer Sciences Journal, vol. 7, no. 1, 2021.
- M. I. Jordan and T. M. Mitchell, "Machine learning: Trends, perspectives, and prospects," Science, vol. 349, no. 6245, pp. 255-260, 2015.
- P. Pinyoanuntapong, P. Janakaraj, R. Balakrishnan, M. Lee, C. Chen, and P. Wang, "Edgeml: towards network-accelerated federated learning over wireless edge," Computer Networks, vol. 219, p. 109396, 2022.
- Y. Jiang et al., "Model pruning enables efficient federated learning on edge devices," IEEE Transactions on Neural Networks and Learning Systems, 2022.
- M. Merouani, M.-H. Leghettas, R. Baghdadi, T. Arbaoui, and K. Benatchba, "A deep learning based cost model for automatic code optimization in tiramisu," PhD thesis, 10 2020, 2020.
- L. T. Khrais, "Investigating of Mobile Learning Technology Acceptance in Companies," Ilkogretim Online, vol. 20, no. 5, 2021.
- Q. Xia, W. Ye, Z. Tao, J. Wu, and Q. Li, "A survey of federated learning for edge computing: Research problems and solutions," High-Confidence Computing, vol. 1, no. 1, p. 100008, 2021.