Title: Impact of machine learning-based traders on the high-frequency stock market
Authors: Kirill Mansurov - Saint-Petersburg State University (Russia) [presenting]
Alexander Semenov - University of Florida and Saint Petersburg State University (United States)
Dmitry Grigoriev - Saint Petersburg State University (Russia)
Rustam Ibragimov - Imperial College London and St. Petersburg State University (United Kingdom)
Abstract: The role of self-learning agents in multi-agent models on financial markets is investigated. We develop an agent-based simulation model of a stock market, and in addition to the agents with fixed strategies used in previous research, we introduce an agent with a self-learning strategy. To model the behavior of such an agent, we use deep reinforcement learning algorithms, namely Deep Deterministicpolicy gradient (DDPG). Next, we conduct a comparative analysis of the results of the constructed model with outcomes of previously proposed models, as well as with the characteristics of real markets. To conduct a comparative analysis, we use stylized facts of asset return that allow us to evaluate and compare the characteristics of the markets. Our results show that a model with a self-learning agent gives a better approximation to the real market than a model with classic agents. In particular, unlike the model with classical agents, the model with a self-learning agent turns out to be not so heavy-tailed. Thus, we demonstrate that for a complete understanding of market processes, simulation models should take into account self-learning agents that have a significant presence on the SP 500 index.