Genetic programming with efficient population control for financial time series prediction
Neal Wagner, Michalewicz, Z. · Adelaide Research & Scholarship (AR&S) (University of Adelaide) · 2001
Genetic Programming (GP) uses variable size representations as solutions. The size of individual solutions in a population can influence the efficiency of the search process. The research presented in this paper compares an alternative method for GP population control to the method commonly found in the literature for the task of financial time series prediction. It is shown that the alternative method gives comparable results with significantly more efficient use of computer resources.