文档介绍：Evolving Rule-Based Trading Systems
  ¡ ¢
Christian Setzkorn , Laura Dipietro , and Robin Purshouse
£
Department puter Science, University of Liverpool, UK
¤
Advanced Robotics and Systems Lab, Scuola Superiore Sant’Anna, Italy
¥
Department of Automatic Control and Systems Engineering, University of Sheffield, UK
Abstract. In this study, a market trading rulebase is optimised using ic pro-
gramming (GP). The rulebase prised of simple relationships between tech-
nical indicators, and generates signals to buy, sell short, and remain inactive. The
methodology is applied to prediction of the Standard & Poor’posite index
(02-Jan-1990 to 18-Oct-2001). Two potential market systems are inferred: a sim-
ple system using few rules and nodes, and a plex system. Results are
compared with a benchmark buy-and-hold strategy. Neither trading system was
found capable of consistently outperforming this benchmark. plicated
rulebases, in addition to being difficult to understand, are susceptible to overfit-
ting. Simpler rulebases are more robust to changing market conditions, but cannot
take advantage of high-profit-making opportunities. By increasing the richness of
the available rulebase building-blocks and the variety of training data, it is antic-
ipated that subsequent systems will surpass the benchmark strategy.
1 Introduction
This paper presents a stu