Reverse Engineering Financial Markets with Majority and Minority Games using Genetic Algorithms

TL;DR

This paper introduces a method to reverse engineer real financial markets by modeling them with agent-based virtual stock markets optimized through genetic algorithms, revealing underlying strategies and predicting market movements.

Contribution

It presents a novel approach combining agent-based modeling, genetic algorithms, and reverse engineering to analyze and predict financial market behavior.

Findings

Successfully reconstructed market parameters and strategies.

Achieved accurate out-of-sample predictions of Nasdaq index movements.

Demonstrated the method's potential for understanding market dynamics.

Abstract

Using virtual stock markets with artificial interacting software investors, aka agent-based models (ABMs), we present a method to reverse engineer real-world financial time series. We model financial markets as made of a large number of interacting boundedly rational agents. By optimizing the similarity between the actual data and that generated by the reconstructed virtual stock market, we obtain parameters and strategies, which reveal some of the inner workings of the target stock market. We validate our approach by out-of-sample predictions of directional moves of the Nasdaq Composite Index.