Evolution of trading strategies with flexible structures: A configuration comparison

Abstract Evolutionary Computation is often used in the domain of automated discovery of trading rules. Within this area, both Genetic Programming and Grammatical Evolution offer solutions with similar structures that have two key advantages in common: they are both interpretable and flexible in terms of their structure. The core algorithms can be extended to use automatically defined functions or mechanisms aimed to promote parsimony. The number of references on this topic is ample, but most of the studies focus on a specific setup. This means that it is not clear which is the best alternative. This work intends to fill that gap in the literature presenting a comprehensive set of experiments using both techniques with similar variations, and measuring their sensitivity to an increase in population size and composition of the terminal set. The experimental work, based on three S&P 500 data sets, suggest that Grammatical Evolution generates strategies that are more profitable, more robust and simpler, especially when a parsimony control technique was applied. As for the use of automatically defined function, it improved the performance in some experiments, but the results were inconclusive.

[1]  Viktor Manahov,et al.  Return predictability and the ‘wisdom of crowds’: Genetic Programming trading algorithms, the Marginal Trader Hypothesis and the Hayek Hypothesis , 2015 .

[2]  Walter Böhm,et al.  Exact Uniform Initialization For Genetic Programming , 1996, FOGA.

[3]  Mukund Seshadri,et al.  GP-evolved Technical Trading Rules Can Outperform Buy and Hold , 2003 .

[4]  Aneta Bera,et al.  A study on the effectiveness of investment strategy based on the concept of pivot points levels using Matthews criterion , 2013 .

[5]  David W. Corne,et al.  Discovering effective technical trading rules with genetic programming: towards robustly outperforming buy-and-hold , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[6]  Fernando E. B. Otero,et al.  Generating Directional Change Based Trading Strategies with Genetic Programming , 2015, EvoApplications.

[7]  Peter Verhoeven,et al.  Does size matter? A genetic programming approach to technical trading , 2010 .

[8]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[9]  Harald Schmidbauer,et al.  Robust trading rule selection and forecasting accuracy , 2014, Journal of Systems Science and Complexity.

[10]  Stephan M. Winkler,et al.  Optimization of Trading Rules for the Spanish Stock Market by Genetic Programming , 2015, IEA/AIE.

[11]  Inés María Galván,et al.  Multiobjective Algorithms with Resampling for Portfolio Optimization , 2014, Comput. Informatics.

[12]  Clara Vega,et al.  Rise of the Machines: Algorithmic Trading in the Foreign Exchange Market: Rise of the Machines , 2014 .

[13]  David W. Corne,et al.  Outperforming Buy-and-Hold with Evolved Technical Trading Rules: Daily, Weekly and Monthly Trading , 2010, EvoApplications.

[14]  Cândida Ferreira,et al.  Automatically Defined Functions in Gene Expression Programming , 2006, Genetic Systems Programming.

[15]  David Quintana,et al.  Robust technical trading strategies using GP for algorithmic portfolio selection , 2016, Expert Syst. Appl..

[16]  Giuseppe Nuti,et al.  Algorithmic Trading , 2011, Computer.

[17]  Anthony Brabazon,et al.  Evolving technical trading rules for spot foreign-exchange markets using grammatical evolution , 2004, Comput. Manag. Sci..

[18]  Bruce Babcock The Dow Jones-Irwin Guide To Trading Systems , 1989 .

[19]  Jean-Yves Potvin,et al.  Generating trading rules on the stock markets with genetic programming , 2004, Comput. Oper. Res..

[20]  Frederico G. Guimarães,et al.  An Automated Investing Method for Stock Market Based on Multiobjective Genetic Programming , 2018 .

[21]  Shu-Heng Chen,et al.  On Predictability and Profitability: Would GP Induced Trading Rules be Sensitive to the Observed Entropy of Time Series? , 2008, Natural Computing in Computational Finance.

[22]  Ulf Johansson,et al.  Co-evolving online high-frequency trading strategies using grammatical evolution , 2014, 2014 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr).

[23]  Christopher J. Neely Risk-adjusted, ex ante, optimal technical trading rules in equity markets , 2003 .

[24]  Thierry Foucault,et al.  News Trading and Speed , 2012 .

[25]  David J. Montana,et al.  Strongly Typed Genetic Programming , 1995, Evolutionary Computation.

[26]  Bruno Biais,et al.  High Frequency Trading , 2012 .

[27]  John L. Person,et al.  A Complete Guide to Technical Trading Tactics: How to Profit Using Pivot Points, Candlesticks & Other Indicators , 2004 .

[28]  Steve Y. Yang,et al.  Genetic programming optimization for a sentiment feedback strength based trading strategy , 2017, Neurocomputing.

[29]  Andrew W. Lo,et al.  Foundations of Technical Analysis: Computational Algorithms, Statistical Inference, and Empirical Implementation , 2000 .

[30]  José Ignacio Hidalgo,et al.  A GA Combining Technical and Fundamental Analysis for Trading the Stock Market , 2012, EvoApplications.

[31]  Anthony Brabazon,et al.  Biologically inspired algorithms for financial modelling , 2006, Natural computing series.

[32]  Alexandros Agapitos,et al.  Genetic Programming with Memory For Financial Trading , 2016, EvoApplications.

[33]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[34]  Akbar Esfahanipour,et al.  A novel approach to dynamic portfolio trading system using multitree genetic programming , 2014, Knowl. Based Syst..

[35]  Michael O'Neill,et al.  Grammatical Evolution: Evolving Programs for an Arbitrary Language , 1998, EuroGP.

[36]  Conor Ryan,et al.  Grammatical Evolution , 2001, Genetic Programming Series.

[37]  John R. Koza Discovery of a Main Program and Reusable Subroutines Using Genetic Programming , 1993 .

[38]  E. Fama EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK* , 1970 .

[39]  Franklin Allen,et al.  Using genetic algorithms to find technical trading rules , 1999 .

[40]  B. LeBaron,et al.  Simple Technical Trading Rules and the Stochastic Properties of Stock Returns , 1992 .

[41]  José Ignacio Hidalgo,et al.  Combining Technical Analysis and Grammatical Evolution in a Trading System , 2013, EvoApplications.

[42]  Colin Fyfe,et al.  Risk adjusted returns from technical trading: a genetic programming approach , 2005 .

[43]  Akbar Esfahanipour,et al.  A genetic programming model to generate risk-adjusted technical trading rules in stock markets , 2011, Expert Syst. Appl..

[44]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[45]  Conor Ryan,et al.  Crossover in Grammatical Evolution: The Search Continues , 2001, EuroGP.

[46]  Cong Quan,et al.  Optimization of Intraday Trading Strategy Based on ACD Rules and Pivot Point System in Chinese Market , 2012 .

[47]  Franz Rothlauf,et al.  Structural difficulty in grammatical evolution versus genetic programming , 2013, GECCO '13.

[48]  Pedro Isasi Viñuela,et al.  Using genetic programming to learn and improve control knowledge , 2002, Artif. Intell..

[49]  Riccardo Poli,et al.  Genetic Programming: An Introduction and Tutorial, with a Survey of Techniques and Applications , 2008, Computational Intelligence: A Compendium.