Evolutionary Approach to Forex Expert Advisor Generation

Alaa Eldin M.  Ibrahim

doi:10.4236/iim.2014.63014

Alaa Eldin M. Ibrahim^*

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.

Keywords: Genetic Algorithms, Forex, Expert Advisors, Trading Strategy

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

References

[1] DeJong, K. (1975) An Analysis of the Behavior of a Class of Genetic Adaptive Systems. Ph.D. Dissertation, Department of Computer and Communication Sciences, University of Michigan, Ann Arbor.

[2] Goldberg, D.E. (1989) Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Publishing Co., Boston.

[3] Grefenstette, J.J. and Baker, J. (1989) How Genetic Algorithms Work: A Critical Look at Implicit Parallelism. Proceedings of 3rd International Conf on Genetic Algorithms, Morgan-Kaufman, 20-27.

[4] Holland, J.H. (1975) Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor.

[5] Simon, D. (2013) Evolutionary Optimization Algorithms, Wiley, Hoboken.

[6] Charles, D. (1859) The Origin of Species. New American Library, New York.

[7] Syswerda, G. (1991) A Study of Reproduction in Generational and Steady-State Genetic Algorithms. Foundations of Genetic Algorithms. Morgan Kaufmann Publishers, 94-101.

[8] Lee, C. (2003) Entropy-Boltzmann Selection in the Genetic Algorithms. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 33, 138-149.
http://dx.doi.org/10.1109/TSMCB.2003.808184

[9] Toffolo, A. and Benini, E. (2003) Genetic Diversity as an Objective in Multi-Objective Evolutionary Algorithms. Evolutionary Computation, 11, 151-167.
http://dx.doi.org/10.1162/106365603766646816

[10] De Jong, E.D., Watson, R.A. and Pollack, J.B. (2001) Reducing Bloat and Promoting Diversity Using Multi-Objective Methods, In: Spector, L., et al., Eds., Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2001), Morgan Kaufmann, San Francisco, 11-18.

[11] Whitley, D. (1989) The Genitor Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trials Is Best. In: Schaffer, J.D., Ed., Proceedings of the 3rd International Conference on Genetic Algorithms, Morgan Kaufmann Publishers, San Mateo, 116-121.

[12] Godart, C. and Kruger, M. (1995) A Genetic Algorithm with Parallel Steady-State Reproduction. In: Alliot, J., et al., Eds., Artificial Evolution, European Conference, Springer, 22-24.

[13] Nicoar, E.S. (2009) Mechanisms to Avoid the Premature Convergence of Genetic Algorithms. Universitatea Petrol-Gaze, din Ploieti, 87-96.

[14] Atsalakisa, G. and Valavanisb, K. (2009) Surveying Stock Market Forecasting Techniques—Part II: Soft Computing Methods. Expert Systems with Applications, 36, 5932-5951.
http://dx.doi.org/10.1016/j.eswa.2008.07.006

[15] Azzini, A., Pereira, C. and Tettamanzi, A. (2009) Predicting Turning Points in Financial Markets with Fuzzy Evolutionary and Neuro-Evolutionary Modelling. Applications of Evolutionary Computing, 5484, 213-222.

[16] Box, G., Jenkins, G. and Reinsel, G. (2006) Time Series Analysis, Forecasting and Control. Prentice Hall, Upper Saddle River.

[17] Myszkowski, P.B. and Bicz, A. (2010) Evolutionary Algorithm in Forex Trade Strategy Generation. Proceedings of the 2010 International Multi-Conference on Computer Science and Information Technology (IMCSIT), Wisla, 18-20 October 2010, 81-88.

[18] Slany, K. (2009) Towards the Automatic Evolutionary Prediction of the FOREX Market Behaviour. International Conference on Adaptive and Intelligent Systems, Klagenfurt, 24-26 September 2009, 141-145.

[19] Yaman, A., Lucci, S. and Gertner, I. (2014) Evolutionary Algorithm Based Approach for Modeling Autonomously Trading Agents. Intelligent Information Management, 6, 45-54.
http://dx.doi.org/10.4236/iim.2014.62007

[20] Ibrahim, A.E. (1998) GenShade: An Evolutionary Approach to Automatic and Interactive Procedural Texture Generation. Ph.D. Dissertation, Texas A&M University, College Station.

[21] GenShade’s ShaderBank Digital Collection 1999-2014, Keywords: Shaderbank Collection. www.turbosquid.com

[22] EATree Software Web Page (2014). www.eatree.com

[23] MetaTrader MQL5 Programming Language Web Page. www.mql5.com