Evolving Rule-Based Trading Systems

In this study, a market trading rulebase is optimised using g enetic programming (GP). The rulebase is comprised of simple relation ships between technical indicators, and generates signals to buy, sell short, and remain inactive. The methodology is applied to prediction of the Standard & Poor’ s composite index (02-Jan-1990 to 18-Oct-2001). Two potential market system are inferred: a simple system using few rules and nodes, and a more complex syste m. R sults are compared with a benchmark buy-and-hold strategy. Neither t rading system was found capable of consistently outperforming this benchmar k. More complicated rulebases, in addition to being difficult to understand, are susceptible to overfitting. Simpler rulebases are more robust to changing market c onditions, but cannot take advantage of high-profit-making opportunities. By inc reasing the richness of the available rulebase building-blocks and the variety of t raining data, it is anticipated that subsequent systems will surpass the benchmark s tr tegy.