Not Available for Download
Add Paper to My Library
Permalink
Using these links will ensure access to this page indefinitely
Copy URL

Genetic Programming for Quantitative Stock Selection

Posted: 7 Apr 2010

See all articles by Ying L. Becker

Ying L. Becker

IBS

Una-May O'Reilly

Massachusetts Institute of Technology

Date Written: March 17, 2009

Abstract

We provide an overview of using genetic programming (GP) to model stock returns. Our models employ GP terminals (model decision variables) that are financial factors identified by experts. We describe the multi-stage training, testing and validation process that we have integrated with GP selection to be appropriate for financial panel data and how the GP solutions are situated within a portfolio selection strategy. We share our experience with the pros and cons of evolved linear and non-linear models, and outline how we have used GP extensions to balance different objectives of portfolio managers and control the complexity of evolved models.

Keywords: Genetic Programming, Genetic Algorithm, Stock Selection,Quantitative Asset Management, Symbolic Regression

JEL Classification: J1, I2

Suggested Citation

Becker, Ying L. and O'Reilly, Una-May, Genetic Programming for Quantitative Stock Selection (March 17, 2009). Available at SSRN: https://ssrn.com/abstract=1585913

Ying L. Becker (Contact Author)

IBS ( email )

Mailstop 32
415 South Street
Waltham, MA MA 02453-2728
United States
508-494-7530 (Phone)

Una-May O'Reilly

Massachusetts Institute of Technology ( email )

Pune
India

Not Available for Download

Do you have a job opening that you would like to promote on SSRN?

Place Job Opening

Paper statistics

Abstract Views
1,574
PlumX Metrics

Related Alerts