A Hybrid System Integrating a Wavelet and TSK Fuzzy Rules for Stock Price Forecasting

The prediction of future time series values based on past and present information is very useful and necessary for various industrial and financial applications. In this study, a novel approach that integrates the wavelet and Takagi-Sugeno-Kang (TSK)-fuzzy-rule-based systems for stock price prediction is developed. A wavelet transform using the Haar wavelet will be applied to decompose the time series in the Haar basis. From the hierarchical scalewise decomposition provided by the wavelet transform, we will next select a number of interesting representations of the time series for further analysis. Then, the TSK fuzzy-rule-based system is employed to predict the stock price based on a set of selected technical indices. To avoid rule explosion, the k-means algorithm is applied to cluster the data and a fuzzy rule is generated in each cluster. Finally, a K nearest neighbor (KNN) is applied as a sliding window to further fine-tune the forecasted result from the TSK model. Simulation results show that the model has successfully forecasted the price variation for stocks with accuracy up to 99.1% in Taiwan Stock Exchange index. Comparative studies with existing prediction models indicate that the proposed model is very promising and can be implemented in a real-time trading system for stock price prediction.

[1]  Kiyoshi Izumi,et al.  Analysis of Exchange Rate Scenarios Using an Artificial Market Approach , 1999, IC-AI.

[2]  Pei-Chann Chang,et al.  A hybrid system by evolving case-based reasoning with genetic algorithm in wholesaler's returning book forecasting , 2006, Decis. Support Syst..

[3]  Ajith Abraham,et al.  Modeling chaotic behavior of stock indices using intelligent paradigms , 2003, Neural Parallel Sci. Comput..

[4]  J. B. Ramsey,et al.  The analysis of foreign exchange data using waveform dictionaries , 1997 .

[5]  JingTao Yao,et al.  Forecasting the KLSE index using neural networks , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[6]  Fionn Murtagh,et al.  Combining Neural Network Forecasts on Wavelet-transformed Time Series , 1997, Connect. Sci..

[7]  Milam W. Aiken,et al.  Forecasting Market Trends with Neural Networks , 1999, Inf. Syst. Manag..

[8]  Cihan H. Dagli,et al.  Stock market prediction using different neural network classification architectures , 1996, IEEE/IAFE 1996 Conference on Computational Intelligence for Financial Engineering (CIFEr).

[9]  Giorgio Guariso,et al.  Coupling fuzzy modeling and neural networks for river flood prediction , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[10]  Khurshid Ahmad,et al.  Testing the Suitability of Wavelet Preprocessing for TSK Fuzzy Models , 2006, 2006 IEEE International Conference on Fuzzy Systems.

[11]  Lawrence Carin,et al.  Application of Haar-wavelet-based multiresolution time-domain schemes to electromagnetic scattering problems , 2002 .

[12]  Renate Sitte,et al.  Analysis of the predictive ability of time delay neural networks applied to the S&P 500 time series , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[13]  Chokri Slim.  Forecasting the Volatility of Stock Index Returns: A Stochastic Neural Network Approach , 2004, ICCSA.

[14]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[15]  Lotfi A. Zadeh,et al.  The role of fuzzy logic in modeling, identification and control , 1996 .

[16]  Kyoung-jae Kim,et al.  Stock market prediction using artificial neural networks with optimal feature transformation , 2004, Neural Computing & Applications.

[17]  Derek A. Linkens,et al.  Rule-base self-generation and simplification for data-driven fuzzy models , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).

[18]  H. White,et al.  Economic prediction using neural networks: the case of IBM daily stock returns , 1988, IEEE 1988 International Conference on Neural Networks.

[19]  David Brownstone,et al.  Using percentage accuracy to measure neural network predictions in Stock Market movements , 1996, Neurocomputing.

[20]  P. Chang,et al.  AN INVESTIGATION OF THE HYBRID FORECASTING MODELS FOR STOCK PRICE VARIATION IN TAIWAN , 2004 .

[21]  Guoqiang Peter Zhang,et al.  Avoiding Pitfalls in Neural Network Research , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[22]  P. Besbeas,et al.  Empirical Bayes approach to block wavelet function estimation , 2002 .

[23]  Jerry M. Mendel,et al.  Generating fuzzy rules by learning from examples , 1991, Proceedings of the 1991 IEEE International Symposium on Intelligent Control.

[24]  V. Alarcon-Aquino,et al.  Multiresolution FIR neural-network-based learning algorithm applied to network traffic prediction , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[25]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[26]  Jacek Mandziuk,et al.  One Day Prediction of NIKKEI Index Considering Information from Other Stock Markets , 2004, ICAISC.

[27]  James B. Ramsey,et al.  The contribution of wavelets to the analysis of economic and financial data , 1999, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[28]  Nikolaos G. Bourbakis,et al.  A neurofuzzy arbitrage simulator for stock investing , 1995, Proceedings of 1995 Conference on Computational Intelligence for Financial Engineering (CIFEr).

[29]  Lawrence Davis,et al.  Training Feedforward Neural Networks Using Genetic Algorithms , 1989, IJCAI.

[30]  Norio Baba,et al.  Utilization of neural networks and GAs for constructing reliable decision support systems to deal stocks , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[31]  Sheng-Chai Chi,et al.  A forecasting approach for stock index future using grey theory and neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[32]  S. Mitra,et al.  Bioinformatics with soft computing , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[33]  Wai Lok Woo,et al.  Neural network approach to blind signal separation of mono-nonlinearly mixed sources , 2005, IEEE Transactions on Circuits and Systems I: Regular Papers.

[34]  Ronald R. Yager,et al.  A framework for fuzzy recognition technology , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[35]  Lakhmi C. Jain,et al.  Fusion of Neural Networks, Fuzzy Sets, and Genetic Algorithms: Industrial Applications , 1998 .

[36]  Jerry M. Mendel,et al.  Generating fuzzy rules by learning from examples , 1992, IEEE Trans. Syst. Man Cybern..

[37]  Pei-Chann Chang,et al.  Combining SOM and fuzzy rule base for flow time prediction in semiconductor manufacturing factory , 2006, Appl. Soft Comput..

[38]  Yanqing Zhang,et al.  Evolutionary fuzzy neural networks for hybrid financial prediction , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[39]  Philip Hans Franses,et al.  The M3 competition: Statistical tests of the results , 2005 .

[40]  Jae Won Lee,et al.  Stock price prediction using reinforcement learning , 2001, ISIE 2001. 2001 IEEE International Symposium on Industrial Electronics Proceedings (Cat. No.01TH8570).

[41]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[42]  Carl G. Looney,et al.  SECURITY MARKET TIMING USING NEURAL NETWORK MODELS , 1997 .

[43]  Teresa Bernarda Ludermir,et al.  Hybrid Technique for Artificial Neural Network Architecture and Weight Optimization , 2005, PKDD.

[44]  Andrew Kusiak,et al.  Planning Product Configurations Based on Sales Data , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[45]  Pei-Chann Chang,et al.  Fuzzy Delphi and back-propagation model for sales forecasting in PCB industry , 2006, Expert Syst. Appl..

[46]  Brandon Whitcher,et al.  Differentiating intraday seasonalities through wavelet multi-scaling , 2001 .

[47]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[48]  Ingoo Han,et al.  Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index , 2000 .

[49]  Fionn Murtagh,et al.  Prediction Based on a Multiscale Decomposition , 2003, Int. J. Wavelets Multiresolution Inf. Process..

[50]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[51]  Ypke Hiemstra,et al.  A stock market forecasting support system based on fuzzy logic , 1994, 1994 Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences.

[52]  K. Ahmad,et al.  Multiscale wavelet preprocessing for fuzzy systems , 2005, 2005 ICSC Congress on Computational Intelligence Methods and Applications.

[53]  Wojciech Ziarko,et al.  A methodology for stock market analysis utilizing rough set theory , 1995, Proceedings of 1995 Conference on Computational Intelligence for Financial Engineering (CIFEr).

[54]  K. Parasuraman,et al.  Wavelet networks: an alternative to classical neural networks , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[55]  Kazuo Asakawa,et al.  Stock market prediction system with modular neural networks , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[56]  Pei-Chann Chang,et al.  A hybrid model by clustering and evolving fuzzy rules for sales decision supports in printed circuit board industry , 2006, Decis. Support Syst..

[57]  Ajith Abraham,et al.  Hybrid Intelligent Systems for Stock Market Analysis , 2001, International Conference on Computational Science.

[58]  I. Daubechies,et al.  Wavelets on the Interval and Fast Wavelet Transforms , 1993 .

[59]  Mu-Chun Su,et al.  Neural-network-based fuzzy model and its application to transient stability prediction in power systems , 1999, IEEE Trans. Syst. Man Cybern. Part C.

[60]  I. Johnstone,et al.  Adapting to Unknown Smoothness via Wavelet Shrinkage , 1995 .

[61]  An-Sing Chen,et al.  Application of Neural Networks to an Emerging Financial Market: Forecasting and Trading the Taiwan Stock Index , 2001, Comput. Oper. Res..

[62]  Amir F. Atiya,et al.  Introduction to financial forecasting , 1996, Applied Intelligence.

[63]  Konstantina Papagiannaki,et al.  Long-term forecasting of Internet backbone traffic , 2005, IEEE Transactions on Neural Networks.

[64]  Shouhong Wang,et al.  A neural network based fuzzy set model for organizational decision making , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[65]  Tsau Young Lin,et al.  Granular neural web agents for stock prediction , 2002, Soft Comput..

[66]  Rimvydas Simutis,et al.  Stocks' Trading System Based on the Particle Swarm Optimization Algorithm , 2004, International Conference on Computational Science.

[67]  Youngohc Yoon,et al.  Predicting stock price performance: a neural network approach , 1991, Proceedings of the Twenty-Fourth Annual Hawaii International Conference on System Sciences.