Using Genetic Programming with Lambda Abstraction to Find Technical Trading Rule

Abstract

Using GP with lambda abstraction module mechanism to generate technical trading rules based on S&P 500 index, we find strong evidence of excess returns over buy-and-hold after transaction cost on the testing period from 1989 to 2002. The rules can be interpreted easily; each uses a combination of one to four widely used technical indicators to make trading decisions. The consensus among GP rules is high, with most of the time 80% of the evolved rules give the same decision. The GP rules give high transaction frequency. Regardless of market climate, they are able to identify opportunities to make profitable trades and out-perform buy-and-hold