ABSTRACT
In foreign exchange (FX) markets, the key issues to achieve profitable trading rules are the combination of the indicators, selection of their parameters, and decision of the trade timing for orders and settlements. In this paper, we present a trading system using a combination of genetic algorithm (GA) and genetic programming (GP). Unlike related researches on this problem, our work focuses on two aspects. First, a calculation of appropriate settlement timing is proposed, to make more profits and less losses. Second, reverse trend data are generated using in-sample data, to overcome the overfitting problem and suppress the risk of loss. To examine the effectiveness of the method, we employed simulations using real-world trading intraday data. It is verified the enhanced capability of our method to make consistent gain out-of-sample and avoid large draw-downs.
- J, Murphy.Technical Analysis of the Financial Markets: A Comprehensive Guide to Trading Method and Applications.Prentice Hall Press, 1999.Google Scholar
- W. Sharpe.Mutual fund performance. Journal of Business, Vol 39, pp.119--138, 1966.Google Scholar
- P. Fernandez-Blanco, D. Bodas-Sagi, F. Soltero, J. I. Hidalgo.Technical Market Indicators Optimization using Evolutionary Algorithms. GECCO 2008, pp. 1851--1857, 2008. Google ScholarDigital Library
- L. Lin, L. Longbing, C. C. Zhang.Genetic Algorithms for Robust Optimization in Financial Applications. In Computational Intelligence 2005, pp.387--391, 2005.Google Scholar
- A. Hirabayashi, C. Aranha, H. Iba.Optimization of the Trading Rule in Foreign Exchange using Genetic Algorithm. In Proceedings of GECCO 2009, pp. 1529--1536, ACM press, 2009. Google ScholarDigital Library
- M. A. H. Dempster and Y. S. Romahi.Intraday FX trading, An evolutionary reinforcement learning approach. In Proceedings of IDEAL 2002, pp 347--358, 2002.\endthebibliography Google ScholarDigital Library
Index Terms
A trading method in FX using evolutionary algorithms: extensions based on reverse trend and settlement timing
Recommendations
Optimization of the trading rule in foreign exchange using genetic algorithm
GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computationThe generation of profitable trading rules for Foreign Exchange (FX) investments is a difficult but popular problem. The use of Machine Learning in this problem allows us to obtain objective results by using information of the past market behavior. In ...
A Comparative Study of Technical Trading Strategies Using a Genetic Algorithm
AbstractTraditional approaches to the study of technical analysis (TA) often focus on the performance of a single indicator, which seems to fall short in scope and depth. We use a genetic algorithm (GA) to optimize trading strategies in the three major ...
Interday foreign exchange trading using linear genetic programming
GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computationForeign exchange (forex) market trading using evolutionary algorithms is an active and controversial area of research. We investigate the use of a linear genetic programming (LGP) system for automated forex trading of four major currency pairs. Fitness ...
Comments