Title page for ETD etd-0430103-121518

Document Type thesis

Author Name Seshadri, Mukund

URN etd-0430103-121518

Title Comprehensibility, Overfitting and Co-Evolution in Genetic Programming for Technical Trading Rules

Degree MS

Department Computer Science

Advisors
Prof. Lee Becker, Advisor
Prof. Carolina Ruiz, Reader
Prof. Micha Hofri, Department Head

Keywords
comprehensiblity
technical analysis
Genetic Programming
overfitting
coevolution cooperative coevolution

Date of Presentation/Defense 2003-04-24

Availability unrestricted

Abstract
This thesis presents Genetic Programming methodologies to find successful and understandable technical trading rules for financial markets. The methods when applied to the S&P500 consistently beat the buy-and-hold strategy over a 12-year period, even when considering transaction costs. Some of the methods described discover rules that beat the S&P500 with 99% significance.
The work describes the use of a complexity-penalizing factor to avoid overfitting and improve comprehensibility of the rules produced by GPs. The effect of this factor on the returns for this domain area is studied and the results indicated that it increased the predictive ability of the rules. A restricted set of operators and domain knowledge were used to improve comprehensibility. In particular, arithmetic operators were eliminated and a number of technical indicators in addition to the widely used moving averages, such as trend lines and local maxima and minima were added. A new evaluation function that tests for consistency of returns in addition to total returns is introduced. Different cooperative coevolutionary genetic programming strategies for improving returns are studied and the results analyzed. We find that paired collaborator coevolution has the best results.

Files
Seshadri.pdf

Browse by Author | Browse by Department | Search all available ETDs

Questions? Email etd-questions@wpi.edu
Maintained by webmaster@wpi.edu

Document Type	thesis
Author Name	Seshadri, Mukund
URN	etd-0430103-121518
Title	Comprehensibility, Overfitting and Co-Evolution in Genetic Programming for Technical Trading Rules
Degree	MS
Department	Computer Science
Advisors	Prof. Lee Becker, Advisor Prof. Carolina Ruiz, Reader Prof. Micha Hofri, Department Head
Keywords	comprehensiblity technical analysis Genetic Programming overfitting coevolution cooperative coevolution
Date of Presentation/Defense	2003-04-24
Availability	unrestricted
Abstract This thesis presents Genetic Programming methodologies to find successful and understandable technical trading rules for financial markets. The methods when applied to the S&P500 consistently beat the buy-and-hold strategy over a 12-year period, even when considering transaction costs. Some of the methods described discover rules that beat the S&P500 with 99% significance. The work describes the use of a complexity-penalizing factor to avoid overfitting and improve comprehensibility of the rules produced by GPs. The effect of this factor on the returns for this domain area is studied and the results indicated that it increased the predictive ability of the rules. A restricted set of operators and domain knowledge were used to improve comprehensibility. In particular, arithmetic operators were eliminated and a number of technical indicators in addition to the widely used moving averages, such as trend lines and local maxima and minima were added. A new evaluation function that tests for consistency of returns in addition to total returns is introduced. Different cooperative coevolutionary genetic programming strategies for improving returns are studied and the results analyzed. We find that paired collaborator coevolution has the best results.
Files	Seshadri.pdf