The influence of smartness on market performance has been discussed for a long time. The smartness of the traders is modeled by the strongly-typed genetic programming (Montana, 1995), which is implemented by using Boolean functions to represent traders' expectations under a constrained syntactic structure. Our simulation results indicate that the greatest profits earners did not employ Boolean functions to form their expectations for approximately 71.66% of the periods. However, they may also benefit from using sophisticated hierarchical thinking. Sometimes, these strategies are quite complicated. In addition, the aggregate behavior induced by the traders with the ability to evolve sophisticated hierarchical thinking can help improve market performance, e.g., less risk, lower transaction costs, and market efficiency.
Published in:
Evolutionary Computation, 2003. CEC '03. The 2003 Congress on
(Volume:4
)
Date of Conference: 8-12 Dec. 2003