On the utility of trading criteria based retraining in forex markets
作者： Alexander Loginov , Malcolm I. Heywood
DOI: 10.1007/978-3-642-37192-9_20
关键词: Foreign exchange market 、 Population 、 Task (project management) 、 Simulation 、 Genetic programming 、 Trading strategy 、 Currency 、 Association (object-oriented programming) 、 Microeconomics 、 Computer science 、 Retraining
摘要: This research investigates the ability of genetic programming (GP) to build profitable trading strategies for Foreign Exchange Market (FX) three major currency pairs (EURUSD, USDCHF and EURCHF) using one hour prices from 2008 2011. We recognize that such environments are likely be non-stationary. Thus, we do not require a single training partition capture all future behaviours. address this by detecting poor behaviours use trigger retraining. In addition task evolving good technical indicators (TI) rules deploying actions is explicitly separated. separate GP populations used coevolve TI under mutualistic symbiotic association. The results 100 simulations demonstrate an adaptive retraining algorithm significantly outperforms single-strategy approach (population evolved once) generates solutions with high probability.
springer.com
sci-hub.st 参考文章(9)
Ian Dempsey, Anthony Brabazon, Michael O'Neill, Foundations in Grammatical Evolution for Dynamic Environments ,(2009)
Wolfgang Banzhaf, Markus F. Brameier, Linear Genetic Programming ,(2006)
Iván Contreras, José Ignacio Hidalgo, Laura Núñez-Letamendia, A GA Combining Technical and Fundamental Analysis for Trading the Stock Market Applications of Evolutionary Computation. pp. 174- 183 ,(2012) , 10.1007/978-3-642-29178-4_18
John A. Doucette, Andrew R. McIntyre, Peter Lichodzijewski, Malcolm I. Heywood, Symbiotic coevolutionary genetic programming: a benchmarking study under large attribute spaces Genetic Programming and Evolvable Machines. ,vol. 13, pp. 71- 101 ,(2012) , 10.1007/S10710-011-9151-4
Aaron Atwater, Malcolm I. Heywood, Nur Zincir-Heywood, GP under streaming data constraints: a case for pareto archiving? genetic and evolutionary computation conference. pp. 703- 710 ,(2012) , 10.1145/2330163.2330262
Clíodhna Tuite, Alexandros Agapitos, Michael O’Neill, Anthony Brabazon, A preliminary investigation of overfitting in evolutionary driven model induction: implications for financial modelling european conference on applications of evolutionary computation. pp. 120- 130 ,(2011) , 10.1007/978-3-642-20520-0_13
Neal Wagner, Zbigniew Michalewicz, Moutaz Khouja, Rob Roy McGregor, Time Series Forecasting for Dynamic Environments: The DyFor Genetic Program Model IEEE Transactions on Evolutionary Computation. ,vol. 11, pp. 433- 452 ,(2007) , 10.1109/TEVC.2006.882430
Michael Mayo, Evolutionary Data Selection for Enhancing Models of Intraday Forex Time Series Applications of Evolutionary Computation. pp. 184- 193 ,(2012) , 10.1007/978-3-642-29178-4_19
Peter Lichodzijewski, Malcolm I. Heywood, Symbiosis, complexification and simplicity under GP genetic and evolutionary computation conference. pp. 853- 860 ,(2010) , 10.1145/1830483.1830640