Impact of the number of AI traders on the market --Micro-foundations of the GARCH model [in Japanese]

Kei Nakagawa, Masanori Hirano, Kentaro Minami, Takanobu Mizuta

The 38th Annual Conference of the Japanese Society for Artificial Intelligence, p. JSAI2024_3Xin201, May 30, 2024

Conference

The 38th Annual Conference of the Japanese Society for Artificial Intelligence

Abstract

Recent developments of machine learning techniques have made AI traders more prominent in financial markets, drawing attention to their market impact. We focus on the GARCH(1,1) model, a key financial time series model, to analyze the influence of AI traders. The GARCH model is the most common method for modeling conditional variance capable of replicating volatility clustering, but its micro-foundations have not yet been fully understood. We categorize market investors into noise traders, fundamental traders, and AI traders and construct the GARCH model with artificial markets using them. We explore how each group affects the GARCH model's parameters and examine the role of AI traders in market dynamics and volatility, using theoretical models and simulations.

Keywords

Multi Agent; Financial Market; Micro Foundation;

doi

10.11517/pjsai.JSAI2024.0_3Xin201

bibtex

@inproceedings{Nakagawa2024-jsai38,
  title={{Impact of the number of AI traders on the market --Micro-foundations of the GARCH model [in Japanese]}},
  author={Kei Nakagawa and Masanori Hirano and Kentaro Minami and Takanobu Mizuta},
  booktitle={The 38th Annual Conference of the Japanese Society for Artificial Intelligence},
  pages={JSAI2024_3Xin201},
  doi={10.11517/pjsai.JSAI2024.0_3Xin201},
  year={2024}
}