Evolutionary Computation and Artificial Financial Markets

Abstract

It is essential not only for investors but for regulators to understand the mechanisms that govern financial markets. However, financial markets are constantly evolving and are becoming more complex and as a consequence more difficult to analyze and understand. Traditional analytical methods cannot explain some of the phenomena which are present in real markets and some of the assumptions that had to be made for the sake of tractability in such models are over-simplistic. This opens the field to alternative methods that allow us to relax some of the most unrealistic assumptions in order to gain a better understanding of such complex systems. Agent-based computational economics (ACE) offers a suitable alternative for the study of financial markets. In this chapter we develop a software platform called Co-evolutionary, Heterogeneous Artificial Stock Market (CHASM); which allows us to perform a series of experiments with the purpose of identifying the aspects that could be responsible for the statistical properties (stylized facts) of financial prices. In CHASM, we model different types of traders: technical, fundamental and noise traders. However, we focus our research on technical traders represented as genetic programming (GP) based agents which co-evolve in the market forecasting price changes on the basis of technical indicators. We perform a detailed exploration of the market’s features in order to identify the conditions under which the stylized facts emerge. Moreover, we develop a behavioral constraint inspired by the Red Queen evolutionary principle to model endogenously the competitive pressure of the market.