Behavioural GP diversity for adaptive stock selection.
(Proceedings) Genetic and Evolutionary Computation (GECCO 2009).
(pp. 1641 - 1648).
We present a new mechanism for preserving phenotypic behavioural diversity in Genetic Programming. We provide a real-world case study for hedge fund portfolio optimization, and experimental results on real-world data that indicate the importance of phenotypic behavioural diversity both in achieving higher fitness and in improving the robustness of the GP population for continuous learning.
|Title:||Behavioural GP diversity for adaptive stock selection|
|Event:||Genetic and Evolutionary Computation (GECCO 2009)|
|Dates:||2009-07-08 - 2009-07-12|
|Keywords:||Genetic Programming, Diversity, Phenotype, Finance, Robustness, Dynamic Environment|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only