Intelligent Information Management

Volume 6, Issue 3 (May 2014)

ISSN Print: 2160-5912   ISSN Online: 2160-5920

Google-based Impact Factor: 1.6  Citations  

Evolutionary Approach to Forex Expert Advisor Generation

HTML  XML Download Download as PDF (Size: 3055KB)  PP. 129-141  
DOI: 10.4236/iim.2014.63014    6,410 Downloads   8,751 Views  Citations

ABSTRACT

We have developed a genetic algorithm approach for automatically generating expert advisors, computer programs that trade automatically in the financial markets. Our system, known as GenFx or Genetic Forex, evaluates evolutionarily generated expert advisors strategies using predetermined fitness functions to automatically prioritize parents for breeding. GenFx simulates several key factors in natural selection. It employs a multiple generation breeding population, a notion of gender, and the concept of aging to maintain diversity while providing many breeding opportunities to highly successful offspring. The approach is also especially efficient running in a multiple processor, multiple selection-strategy mode using multiple settings. We found out that a multi-processor gender-based running of the system outperformed all single runs of the system. This system is inspired by GenShade, a previous system that we have developed for evolutionary generating procedural textures. The methods described in this paper are not limited to the Forex market or financial problems only but are applicable to many other fields.

Share and Cite:

Ibrahim, A. (2014) Evolutionary Approach to Forex Expert Advisor Generation. Intelligent Information Management, 6, 129-141. doi: 10.4236/iim.2014.63014.

Cited by

No relevant information.

Copyright © 2024 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.