MGP-INTACTSKY: Multitree Genetic Programming-based learning of INTerpretable and ACcurate TSK sYstems for dynamic portfolio trading

MGP-INTACTSKY is a fuzzy rule based system for dynamic portfolio trading.Multitree Genetic Programming (MGP) is applied to learn the TSK fuzzy rule bases.The new TSK structure leads to a more interpretable and accurate system.Input variables are technical indices selected by stepwise regression analysis.The results are based on testing of the model on one emerging and two mature markets. In this paper, a Multitree Genetic Programming-based method is developed to learn an INTerpretable and ACcurate Takagi-Sugeno-Kang (TSK) fuzzy rule based sYstem (MGP-INTACTSKY) for dynamic portfolio trading. The MGP-INTACTSKY utilizes a TSK model with a new structure to develop a more interpretable and accurate system for dynamic portfolio trading. In the new structure of TSK, disjunctive normal form rules with variable structured consequent parts are developed in which the absence of some input variables is allowed. Input variables are the most influential technical indices which are selected by stepwise regression analysis. The technical indices are computed using wavelet transformed stock price series to eliminate the noise. The proposed system directly induces the preferred portfolio weights from the stock's technical indices through time. Here, genetic programming with the multitree structure is applied to learn the TSK fuzzy rule bases with the Pittsburgh approach. With this approach, the correlation of different stocks is properly considered during the evolutionary process. To evaluate the performance of the MGP-INTACTSKY for portfolio trading, the proposed model is implemented on the Tehran Stock Exchange as an emerging market as well as Toronto and Frankfurt Stock Exchanges as two mature markets. The experimental results show that the proposed model outperforms other methods such as the momentum strategy, the multitree genetic programming-based crisp system, the genetic algorithm-based first order TSK system, the buy and hold approach and the market's main index in terms of accuracy and interpretability.

[1]  Jui-Chung Hung,et al.  A fuzzy GARCH model applied to stock market scenario using a genetic algorithm , 2009, Expert Syst. Appl..

[2]  Francisco Herrera,et al.  Genetic fuzzy systems: taxonomy, current research trends and prospects , 2008, Evol. Intell..

[3]  George W. Irwin,et al.  A New Gradient Descent Approach for Local Learning of Fuzzy Neural Models , 2013, IEEE Transactions on Fuzzy Systems.

[4]  Wei-Chang Yeh,et al.  Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm , 2011, Appl. Soft Comput..

[5]  Hitoshi Iba,et al.  Using memetic algorithms to improve portfolio performance in static and dynamic trading scenarios , 2009, GECCO.

[6]  Zbigniew Michalewicz,et al.  Computational Intelligence for Evolving Trading Rules , 2009, IEEE Transactions on Evolutionary Computation.

[7]  John L. Maginn.  Managing Investment Portfolios: A Dynamic Process , 2008 .

[8]  Stephen F. Smith,et al.  A learning system based on genetic adaptive algorithms , 1980 .

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

[10]  Chia-Feng Juang,et al.  Reduced Interval Type-2 Neural Fuzzy System Using Weighted Bound-Set Boundary Operation for Computation Speedup and Chip Implementation , 2013, IEEE Transactions on Fuzzy Systems.

[11]  Manuel Mucientes,et al.  Processing time estimations by variable structure TSK rules learned through genetic programming , 2008, Soft Comput..

[12]  Oscar Castillo,et al.  New approach using ant colony optimization with ant set partition for fuzzy control design applied to the ball and beam system , 2015, Inf. Sci..

[13]  Hojjat Adeli,et al.  Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems , 1994 .

[14]  田口 玄一,et al.  System of experimental design : engineering methods to optimize quality and minimize costs , 1987 .

[15]  Abaxbank,et al.  Spectral Measures of Risk : a Coherent Representation of Subjective Risk Aversion , 2002 .

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

[17]  Francisco Herrera,et al.  A Multiobjective Evolutionary Approach to Concurrently Learn Rule and Data Bases of Linguistic Fuzzy-Rule-Based Systems , 2009, IEEE Transactions on Fuzzy Systems.

[18]  Mohammad Hossein Fazel Zarandi,et al.  A type-2 fuzzy rule-based expert system model for stock price analysis , 2009, Expert Syst. Appl..

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

[20]  Héctor Pomares,et al.  TaSe, a Taylor series-based fuzzy system model that combines interpretability and accuracy , 2005, Fuzzy Sets Syst..

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

[22]  Pei-Chann Chang,et al.  A TSK type fuzzy rule based system for stock price prediction , 2008, Expert Syst. Appl..

[23]  Stphane Mallat,et al.  A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way , 2008 .

[24]  He Ni.  Profitability of Technical Chart Pattern Trading on FX Rates: Analyzed by Wavelet Transform , 2009, 2009 Third International Symposium on Intelligent Information Technology Application.

[25]  Esmaeil Hadavandi,et al.  Hybridization of evolutionary Levenberg-Marquardt neural networks and data pre-processing for stock market prediction , 2012, Knowl. Based Syst..

[26]  Luis Magdalena,et al.  Interpretability Improvements to Find the Balance Interpretability-Accuracy in Fuzzy Modeling: An Overview , 2003 .

[27]  F. Herrera,et al.  Accuracy Improvements in Linguistic Fuzzy Modeling , 2003 .

[28]  Hitoshi Iba,et al.  Modelling cost into a genetic algorithm-based portfolio optimization system by seeding and objective sharing , 2007, 2007 IEEE Congress on Evolutionary Computation.

[29]  Genichi Taguchi.  System Of Experimental Design: Engineering Methods To Optimize Quality And Minimize Costs , 1987 .

[30]  Andries P. Engelbrecht,et al.  A Building Block Approach to Genetic Programming for Rule Discovery , 2002 .

[31]  Hisao Ishibuchi,et al.  Comparison of the Michigan and Pittsburgh approaches to the design of fuzzy classification systems , 1997 .

[32]  K. S. Ramaswami,et al.  Integration of SRA, ANFIS and CAPM for stock portfolio management , 2013, CSI Transactions on ICT.

[33]  C. H. Chen,et al.  An intelligent stock trading decision support system through integration of genetic algorithm based fuzzy neural network and artificial neural network , 2001, Fuzzy Sets Syst..

[34]  Jesús Alcalá-Fdez,et al.  Hybrid learning models to get the interpretability–accuracy trade-off in fuzzy modeling , 2006, Soft Comput..

[35]  Shingo Mabu,et al.  A model of portfolio optimization using time adapting genetic network programming , 2010, Comput. Oper. Res..

[36]  Fakhri Karray,et al.  Soft Computing and Tools of Intelligent Systems Design: Theory and Applications , 2004 .

[37]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing - The Sparse Way, 3rd Edition , 2008 .

[38]  Tang-Kai Yin,et al.  A characteristic-point-based fuzzy inference system aimed to minimize the number of fuzzy rules , 2004, IEEE Trans. Fuzzy Syst..

[39]  Antonio González Muñoz,et al.  Table Ii Tc Pattern Recognition Result for 120 Eir Satellite Image Cases Selection of Relevant Features in a Fuzzy Genetic Learning Algorithm , 2001 .

[40]  Sheng-Tun Li,et al.  Knowledge discovery in financial investment for forecasting and trading strategy through wavelet-based SOM networks , 2008, Expert Syst. Appl..

[41]  Ming Su,et al.  A generalized TSK model with a novel rule antecedent structure: Structure identification and parameter estimation , 2010, Comput. Chem. Eng..

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

[43]  Nikhil R. Pal,et al.  A novel approach to design classifiers using genetic programming , 2004, IEEE Transactions on Evolutionary Computation.

[44]  Fakhreddine O. Karray,et al.  Soft Computing and Intelligent Systems Design, Theory, Tools and Applications , 2006, IEEE Transactions on Neural Networks.

[45]  Hisao Ishibuchi,et al.  Classification and modeling with linguistic information granules - advanced approaches to linguistic data mining , 2004, Advanced information processing.

[46]  Riccardo Poli,et al.  A Field Guide to Genetic Programming , 2008 .

[47]  Arash Ghanbari,et al.  Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting , 2010, Knowl. Based Syst..

[48]  Alex Alves Freitas,et al.  A constrained-syntax genetic programming system for discovering classification rules: application to medical data sets , 2004, Artif. Intell. Medicine.

[49]  Pei-Chann Chang,et al.  A novel model by evolving partially connected neural network for stock price trend forecasting , 2012, Expert Syst. Appl..

[50]  Oscar Castillo,et al.  Fuzzy System Optimization Using a Hierarchical Genetic Algorithm Applied to Pattern Recognition , 2014, IEEE Conf. on Intelligent Systems.

[51]  Yan Chen,et al.  A hybrid stock trading system using genetic network programming and mean conditional value-at-risk , 2015, Eur. J. Oper. Res..

[52]  Andreas Bastian.  Identifying fuzzy models utilizing genetic programming , 2000, Fuzzy Sets Syst..

[53]  Yeung Yam,et al.  Reduction of fuzzy rule base via singular value decomposition , 1999, IEEE Trans. Fuzzy Syst..

[54]  Hasan Selim,et al.  A fuzzy rule based expert system for stock evaluation and portfolio construction: An application to Istanbul Stock Exchange , 2013, Expert Syst. Appl..

[55]  John Yen,et al.  Improving the interpretability of TSK fuzzy models by combining global learning and local learning , 1998, IEEE Trans. Fuzzy Syst..

[56]  F. Herrera,et al.  Accuracy Improvements to Find the Balance Interpretability-Accuracy in Linguistic Fuzzy Modeling: An Overview , 2003 .

[57]  Wei Yan,et al.  Learning to optimize profits beats predicting returns -: comparing techniques for financial portfolio optimisation , 2008, GECCO '08.

[58]  Antonio J. Rivera,et al.  GP-COACH: Genetic Programming-based learning of COmpact and ACcurate fuzzy rule-based classification systems for High-dimensional problems , 2010, Inf. Sci..

[59]  Pei-Chann Chang,et al.  A Hybrid System Integrating a Wavelet and TSK Fuzzy Rules for Stock Price Forecasting , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[60]  Longbing Cao,et al.  Minimax Probability TSK Fuzzy System Classifier: A More Transparent and Highly Interpretable Classification Model , 2015, IEEE Transactions on Fuzzy Systems.

[61]  José Manuel Andújar Márquez,et al.  A new methodology to improve interpretability in neuro-fuzzy TSK models , 2010, Appl. Soft Comput..

[62]  Hisao Ishibuchi,et al.  Analysis of interpretability-accuracy tradeoff of fuzzy systems by multiobjective fuzzy genetics-based machine learning , 2007, Int. J. Approx. Reason..

[63]  Francisco Herrera,et al.  Cooperative Evolutionary Learning of Linguistic Fuzzy Rules and Parametric Aggregation Connectors for Mamdani Fuzzy Systems , 2007, IEEE Transactions on Fuzzy Systems.

[64]  Oscar Castillo,et al.  A multi-objective optimization of type-2 fuzzy control speed in FPGAs , 2014, Appl. Soft Comput..

[65]  Masaaki Kijima,et al.  On the significance of expected shortfall as a coherent risk measure , 2005 .

[66]  Manuel Laguna,et al.  Fine-Tuning of Algorithms Using Fractional Experimental Designs and Local Search , 2006, Oper. Res..

[67]  Akbar Esfahanipour,et al.  Adapted Neuro-Fuzzy Inference System on indirect approach TSK fuzzy rule base for stock market analysis , 2010, Expert Syst. Appl..

[68]  Jorge Casillas,et al.  Consistent, Complete and Compact Generation of DNF-type Fuzzy Rules by a Pittsburgh-style Genetic Algorithm , 2007, 2007 IEEE International Fuzzy Systems Conference.

[69]  Athanasios Tsakonas,et al.  A comparison of classification accuracy of four genetic programming-evolved intelligent structures , 2006, Inf. Sci..

[70]  Francisco Herrera,et al.  A Review of the Application of Multiobjective Evolutionary Fuzzy Systems: Current Status and Further Directions , 2013, IEEE Transactions on Fuzzy Systems.

[71]  Nuno Horta,et al.  Applying a GA kernel on optimizing technical analysis rules for stock picking and portfolio composition , 2011, Expert Syst. Appl..

[72]  Christopher D. Clack,et al.  Robustness of multiple objective GP stock-picking in unstable financial markets: real-world applications track , 2009, GECCO.

[73]  Jorge Casillas,et al.  Special issue on “Genetic Fuzzy Systems: Recent Developments and Future Directions” , 2009, Soft Comput..

[74]  Peter W.H. Smith,et al.  Genetic Programming as a Data-Mining Tool , 2002 .