This paper describes a set of experiments performed with an artificial futures market simulation. The non-rational market participants, which evolve simple strategies using genetic algorithms, compete against each other to make profits by buying and selling futures contracts. The dynamic and equilibrium behavior of the participants is studied under a variety of conditions. The results suggest that in simple markets with non-homogenous participants opportunities for making consistent profits over extended periods of time exist. Introduction Although futures contracts are a relatively recent addition to the cornucopia of financial products available to market participants, their rate of growth has positioned them as one of the most traded financial vehicles in the world. Scalpers, day traders, institutions, and hedgers all compete to exchange risk and return in ways that meet their objectives. All participants in the market have data about the cumulative actions of all of the other part...

In this chapter we describe a stock market simulation in which stock market participants use genetic algorithms to gradually improve their trading strategies over time. A variety of experiments show that, under certain conditions, some market participants can make consistent profits over an extended period of time, a finding that might explain the success of some real-world money managers. These experiments suggest a four parameter model of market participants. Each participant can be described along four dimensions: information set, constraint set, algorithm set, and model set. The information set captures what data the participant has access to (e.g., the participant has access to all historical price data). The constraint set describes under what restrictions the participant operates (e.g., the participant can borrow money at 1% above the prime rate). The algorithm set indicates what programs the participant can use (e.g., the participant is restricted to hill-climbing optimization ...