Towards Evology: A Market Ecology Agent-Based Model
Our paper, Towards Evology: a Market Ecology Agent-Based Model of US Equity Mutual Funds, was presented at the Benchmarks in AI workshop at the ACM International Conference on AI in Finance (ICAIF) 2022.
It is joint work with Aymeric Vié, Alissa M. Kleinnijenhuis, and J. Doyne Farmer. Evology is an empirically calibrated agent-based model that treats the market as an ecosystem of interacting strategies. Where the PNAS paper made the market-ecology argument in a toy model, Evology calibrates the idea to real US equity mutual funds — value and growth styles included — so the interactions between strategies, and their effect on returns, are endogenous rather than assumed.
The model and calibration are in the paper.