Parallel Evolutionary Algorithms for Stock Market Trading Rule Selection on Many-Core Graphics Processors

This chapter concerns stock market decision support systems that build trading expertise on the basis of a set of specific trading rules, analysing financial time series of recent stock price quotations, and focusses on the process of rule selection. It proposes an improvement of two popular evolutionary algorithms for rule selection by reinforcing them with two local search operators. The algorithms are also adapted for parallel processing on many-core graphics processors. Using many-core graphics processors enables not only a reduction in the computing time, but also an exhaustive local search, which significantly improves solution quality, without increasing computing time. Experiments carried out on data from the Paris Stock Exchange confirmed that the approach proposed outperforms the classic approach, in terms of the financial relevance of the investment strategies discovered as well as in terms of the computing time.

[1]  Brad G. Kyer.  Review of 5 of biologically inspired algorithms for financial modelling by Anthony Brabazon, Michael O'Neill Springer-Verlag Berlin Heidelberg, 2006 , 2010, SIGA.

[2]  Pedro Larrañaga,et al.  Estimation of Distribution Algorithms , 2002, Genetic Algorithms and Evolutionary Computation.

[3]  W. Sharpe.  CAPITAL ASSET PRICES: A THEORY OF MARKET EQUILIBRIUM UNDER CONDITIONS OF RISK* , 1964 .

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

[5]  Jerzy J. Korczak,et al.  Evolutionary building of stock trading experts in a real-time system , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[6]  Andreas Kolb,et al.  GPU-Based Multilevel Clustering , 2011, IEEE Transactions on Visualization and Computer Graphics.

[7]  John Domingue,et al.  Artificial Intelligence: Methodology, Systems, and Applications, 12th International Conference, AIMSA 2006, Varna, Bulgaria, September 12-15, 2006, Proceedings , 2006, AIMSA.

[8]  Tony Plummer.  Forecasting financial markets , 1993 .

[9]  Anthony Brabazon,et al.  Adaptive Trading With Grammatical Evolution , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[10]  Shumeet Baluja,et al.  A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning , 1994 .

[11]  Jin Li,et al.  EDDIE In Financial Decision Making , 2001 .

[12]  Asim Munawar,et al.  A Bayesian Optimization Algorithm for De Novo ligand design based docking running over GPU , 2010, IEEE Congress on Evolutionary Computation.

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

[14]  Alessandro Artusi,et al.  Radial Basis Function Networks GPU-Based Implementation , 2008, IEEE Transactions on Neural Networks.

[15]  Piotr Lipinski.  Evolutionary Decision Support System for Stock Market Trading , 2008, AIMSA.

[16]  Rolf Drechsler,et al.  Applications of Evolutionary Computing, EvoWorkshops 2008: EvoCOMNET, EvoFIN, EvoHOT, EvoIASP, EvoMUSART, EvoNUM, EvoSTOC, and EvoTransLog, Naples, Italy, March 26-28, 2008. Proceedings , 2008, EvoWorkshops.

[17]  Piotr Lipinski.  Evolutionary Strategies for Building Risk-Optimal Portfolios , 2008, Natural Computing in Computational Finance.

[18]  Anthony Brabazon,et al.  Natural Computing in Computational Finance , 2008, Natural Computing in Computational Finance.

[19]  Anthony Brabazon,et al.  Estimation of an EGARCHVolatility Option Pricing Model using a Bacteria Foraging Optimisation Algorithm , 2008, Natural Computing in Computational Finance.

[20]  Dietmar Maringer,et al.  Evolutionary Money Management , 2009, EvoWorkshops.

[21]  J. A. Lozano,et al.  Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation , 2001 .