Reproduce “A Multi-agent Market Model Can Explain the Impact of AI Traders in Financial Markets -- A New Microfoundations of GARCH model” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Kei Nakagawa, Masanori Hirano, Kentaro Minami, Takanobu Mizuta
A multi-agent market model establishes microfoundations for the GARCH(1,1) model, deriving its parameters from the interactions of noise, fundamental, and AI traders, and quantitatively reproduces key financial market stylized facts like volatility clustering and fat tails.
Key insights
- The GARCH alpha parameter, representing sensitivity to past price shocks, is directly linked to the proportion and risk aversion of AI traders (p2^2 gamma^2).
- The GARCH beta parameter, indicating the persistence of volatility, is linked to the risk aversion and proportion of fundamental traders (p1^2 lambda^2).
- The model reveals how specific market stylized facts, such as baseline volatility, volatility clustering, and responsiveness to shocks, emerge from the presence and interaction of distinct trader types.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.