Evolving ab initio trading strategies in heterogeneous environments

TL;DR

This paper presents a method for evolving neural network-based trading strategies within a simulated market environment, demonstrating their profitability across various real-world market conditions without prior exposure to actual data.

Contribution

It introduces an evolutionary framework for developing ab initio trading algorithms using agent-based market simulations, bypassing traditional data-driven training.

Findings

Evolved trading agents outperform baseline strategies.

Superdiffusion phenomena observed during evolution.

Evolved algorithms are profitable on real high-frequency FX data.

Abstract

Securities markets are quintessential complex adaptive systems in which heterogeneous agents compete in an attempt to maximize returns. Species of trading agents are also subject to evolutionary pressure as entire classes of strategies become obsolete and new classes emerge. Using an agent-based model of interacting heterogeneous agents as a flexible environment that can endogenously model many diverse market conditions, we subject deep neural networks to evolutionary pressure to create dominant trading agents. After analyzing the performance of these agents and noting the emergence of anomalous superdiffusion through the evolutionary process, we construct a method to turn high-fitness agents into trading algorithms. We backtest these trading algorithms on real high-frequency foreign exchange data, demonstrating that elite trading algorithms are consistently profitable in a variety of market conditions---even though these algorithms had never before been exposed to real financial data. These results provide evidence to suggest that developing \textit{ab initio} trading strategies by repeated simulation and evolution in a mechanistic market model may be a practical alternative to explicitly training models with past observed market data.