A Multi-Agent Approach to Market Microstructure Modeling: AI Perspectives on Financial Liquidity
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V2I3P103Keywords:
Market Microstructure, Artificial Intelligence, Multi-Agent Systems, Financial Liquidity, Reinforcement Learning, Limit Order Book, Algorithmic Trading, Price Discovery, Simulation, Deep LearningAbstract
Some considerations of the working of the financial markets form part of the basis of theoretical and practical finance. Market microstructure on how securities are traded, and prices are determined has been impacted on by algorithmic trading and Artificial Intelligence (AI). In this paper, a new approach to modeling the financial liquidity of a company is suggested, characterized by using a Multi-Agent System prototype with artificial intelligence built inside the acting agents. It will assess how heterogeneous agents, through their behavior and interaction, impact the aspects of market liquidity, bid-ask spreads, volatilities, and price discovery. The current paper proposes the theory of using intelligent agents, RL, and supervised learning to incorporate institutional traders, market makers, and retail investors. The proposed work involves implementing a simulation environment that models a LOB and uses real market data for evaluation. Pursuant to this, the simulations reveal that the AI-enhanced multi-agent models provide a near-perfect simulation of the actual markets and, more importantly, provide a better understanding of the microstructure of the markets in relation to information asymmetry and order strategies of the various players in the market. Therefore, agent-based decisions employing neural network-based decision functions show complexity, such as clustering, flash crashes, and temporary illiquidity. They are examined via several market indicators and representations. Furthermore, it is evaluated under various regulatory and market conditions, such as circuit breakers and liquidity injections, to derive policies. This paper’s scholarly contribution would be an attempt to move the debate beyond the current vehicle of analysis that is predominantly constituted by economic theories and frameworks and seek the help of AI techniques in doing so
References
[1] Van der Hoek, W., & Wooldridge, M. (2008). Multi-agent systems. Foundations of Artificial Intelligence, 3, 887-928.
[2] Ferber, J., & Weiss, G. (1999). Multi-agent systems: an introduction to distributed artificial intelligence (Vol. 1). Reading: Addison-wesley.
[3] Uhrmacher, A. M., & Weyns, D. (Eds.). (2018). Multi-Agent systems: Simulation and applications. CRC press.
[4] Grzonka, D., Jakóbik, A., Kołodziej, J., & Pllana, S. (2018). Using a multi-agent system and artificial intelligence to monitor and improve cloud performance and security. Future generation computer systems, 86, 1106-1117.
[5] Tweedale, J., Ichalkaranje, N., Sioutis, C., Jarvis, B., Consoli, A., & Phillips-Wren, G. (2007). Innovations in multi-agent systems. Journal of Network and Computer Applications, 30(3), 1089-1115.
[6] Glosten, L. R., & Milgrom, P. R. (1985). Bid, ask, and transaction prices in a specialist market with heterogeneously informed traders. Journal of financial economics, 14(1), 71-100.
[7] Kyle, A. S. (1985). Continuous auctions and insider trading. Econometrica: Journal of the Econometric Society, 1315-1335.
[8] O'Hara, M. (1998). Market microstructure theory. John Wiley & Sons.
[9] Madhavan, A. (2000). Market microstructure: A survey. Journal of financial markets, 3(3), 205-258.
[10] Lux, T., & Marchesi, M. (1999). Scaling and criticality in a stochastic multi-agent model of a financial market. Nature, 397(6719), 498-500.
[11] LeBaron, B. (2006). Agent-based computational finance. Handbook of computational economics, 2, 1187-1233.
[12] Tesfatsion, L., & Judd, K. L. (Eds.). (2006). Handbook of computational economics: agent-based computational economics (Vol. 2). Elsevier.
[13] Chen, S. H., & Yeh, C. H. (2001). Evolving traders and the business school with genetic programming: A new agent-based artificial stock market architecture. Journal of Economic Dynamics and Control, 25(3-4), 363-393.
[14] Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert systems with applications, 42(1), 259-268.
[15] Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European journal of operational research, 270(2), 654-669.
[16] Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short-term memory. PloS one, 12(7), e0180944.
[17] Heaton, J. B., Polson, N. G., & Witte, J. H. (2016). Deep learning in finance. arXiv preprint arXiv:1602.06561.
[18] Moody, J., & Saffell, M. (2001). Learning to trade via direct reinforcement. IEEE transactions on neural Networks, 12(4), 875-889.
[19] Nevmyvaka, Y., Feng, Y., & Kearns, M. (2006, June). Reinforcement learning for optimized trade execution. In Proceedings of the 23rd International Conference on Machine Learning (pp. 673-680).
[20] Jiang, Z., Xu, D., & Liang, J. (2017). A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:1706.10059.
