Abstract
One of the most critical issues that developers face in developing automatic systems for electronic markets is that of endowing the agents with appropriate trading strategies. In this article, we examine the problem in the foreign exchange (FX) market, and we use an agent-based market simulation to examine which trading strategies lead to market states in which the stylized facts (statistical properties) of the simulation match those of the FX market transactions data. Our goal is to explore the emergence of the stylized facts, when the simulated market is populated with agents using different strategies: a variation of the zero intelligence with a constraint strategy, the zero-intelligence directional-change event strategy, and a genetic programming-based strategy. A series of experiments were conducted, and the results were compared with those of a high-frequency FX transaction data set. Our results show that the zero-intelligence directional-change event agents best reproduce and explain the properties observed in the FX market transactions data. Our study suggests that the observed stylized facts could be the result of introducing a threshold that triggers the agents to respond to periodic patterns in the price time series. The results can be used to develop decision support systems for the FX market.