Does more intelligent trading strategy win? Interacting trading strategies: an agent-based approach

Beyhan H., Ulengin B.

Journal of Intelligence Studies in Business, vol.12, no.3, pp.54-65, 2023 (ESCI) identifier

  • Publication Type: Article / Article
  • Volume: 12 Issue: 3
  • Publication Date: 2023
  • Doi Number: 10.37380/jisib.v12i3.929
  • Journal Name: Journal of Intelligence Studies in Business
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, Business Source Elite, Business Source Premier, Directory of Open Access Journals
  • Page Numbers: pp.54-65
  • Keywords: Agent based model, ARIMA, Machine Learning, Multi-Agent Financial Market
  • Istanbul Technical University Affiliated: Yes

Abstract

An artificial financial market is built on the top of Genoa Artificial Stock Market. The market is populated with agents having different trading strategies and they are let to interact with each other. Agents differ in the trading method they use to trade, and they are grouped as noise, technical, statistical analysis, and machine learning traders. The model is validated by replication of stylized fact in financial asset returns. We were able to replicate leptokurtic shape of probability density function, volatility clustering and absence of autocorrelation in asset returns. The wealth dynamics for each agent group is analysed throughout trading period. Agents with a higher time complexity trading strategy outperform those with strategy comparing their final wealth.