Survival of the Chartist: An Evolutionary Agent-Based Analysis of Stock Market Trading

A stock market is a highly complex dynamical system. Stock-price movements are not solely driven by fundamental values but in particular influenced by short term trading behaviour. Chartists use trends to forecast future price directions, whereas fundamentalists estimate stock prices based on dividend payouts or company earnings. Such strategies can similarly be deployed in automatic trading agents, which already account for a large portion of current trading activity. It is therefore vital to understand how these trading strategies behave in different scenarios, and how the interplay of strategies may lead to various market outcomes. In this paper we analyse the dynamics of three different trading strategies: fundamentalist, chartist, and zero-information traders, who base their trading behaviour on the current market price only. We simulate stock markets with various constellations of trading agents, and compare their evolutionary strength, using heuristic payoff tables and the replicator dynamics of evolutionary game theory. Our results show that it is not straightforward to predict in advance which trading strategy will perform best. Fundamentalists outperform other traders, and drive them out of the market, when information is freely available. If fundamental information is costly, chartists may thrive. As such, this paper sheds light on the various factors that play a role in determining success or failure of trading strategies in a complex market.

[1]  E. Fama.  EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK* , 1970 .

[2]  J. Fred Weston,et al.  The Investment, Financing, and Valuation of the Corporation. , 1963 .

[3]  Peter McBurney,et al.  Trading in markets with noisy information: an evolutionary analysis , 2015, Connect. Sci..

[4]  Lukas Menkhoff,et al.  Extended evidence on the use of technical analysis in foreign exchange , 2006 .

[5]  Yoav Shoham,et al.  If multi-agent learning is the answer, what is the question? , 2007, Artif. Intell..

[6]  Jing Gao,et al.  Multistep-Ahead Time Series Prediction , 2006, PAKDD.

[7]  G. Burton.  MALKIEL, . The Efficient Market Hypothesis and Its Critics, Journal of Economic Perspectives, , . , 2003 .

[8]  M. Gordon,et al.  Dividends, Earnings, and Stock Prices , 1959 .

[9]  R. Cont.  Empirical properties of asset returns: stylized facts and statistical issues , 2001 .

[10]  Simon Parsons,et al.  Evolutionary advantage of foresight in markets , 2012, GECCO '12.

[11]  Peter McBurney,et al.  An evolutionary game-theoretic comparison of two double-auction market designs , 2004, AAMAS'04.

[12]  Trading behavior and profits in experimental asset markets with asymmetric information , 2014 .

[13]  J. Huber,et al.  The value of information in a multi-agent market model , 2006, physics/0610026.

[14]  B. Malkiel.  The Efficient Market Hypothesis and Its Critics , 2003 .

[15]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[16]  E. Fama.  The Behavior of Stock-Market Prices , 1965 .

[17]  Simon Parsons,et al.  What evolutionary game theory tells us about multiagent learning , 2007, Artif. Intell..

[18]  Simon Parsons,et al.  An evolutionary model of multi-agent learning with a varying exploration rate , 2009, AAMAS.

[19]  Mark P. Taylor,et al.  The use of technical analysis in the foreign exchange market , 1992 .

[20]  Ali Hortaçsu,et al.  Winner's Curse, Reserve Prices and Endogenous Entry: Empirical Insights from Ebay Auctions , 2003 .

[21]  E. Scalas,et al.  The value of information in financial markets: An agent-based simulation , 2007, 0712.2687.

[22]  G. Tesauro,et al.  Analyzing Complex Strategic Interactions in Multi-Agent Systems , 2002 .

[23]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[24]  M. Sutter,et al.  Is more information always better?: Experimental financial markets with cumulative information , 2008 .