Forecasting Exchange Rates: A Neuro-Fuzzy Approach

This paper presents an adaptive neuro-fuzzy inference system (ANFIS) for USD/JPY exchange rates forecasting. Previous work often used time series techniques and neural networks (NN). ANFIS can be used to better explain solutions to users than completely black-box models, such as NN. The proposed neurofuzzy rule based system applies some technical and fundamental indexes as input variables. In order to generate membership functions (MFs), we make use of fuzzy clustering of the output space. The neuro-fuzzy model is tested with 28 candidate input variables for both currencies. For the purpose of comparison, Sugeno-Yasukawa model, feedforward multi-layer neural network, and multiple regression are benchmarked. The comparison demonstrates that the presented algorithm shows its superiority in terms of prediction error minimization, robustness and flexibility. Keywords— ANFIS Network, Exchange Rates, Forecasting, Neuro-Fuzzy Systems, Nonlinear Identification.

[1]  David Hsieh.  Chaos and Nonlinear Dynamics: Application to Financial Markets , 1991 .

[2]  G. M. Varazi,et al.  Constructive algorithm for neuro-fuzzy networks , 1997, Proceedings of 6th International Fuzzy Systems Conference.

[3]  Mu-Song Chen,et al.  A comparative study of learning methods in tuning parameters of fuzzy membership functions , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[4]  Young-Il Kim,et al.  A cluster validation index for GK cluster analysis based on relative degree of sharing , 2004, Inf. Sci..

[5]  Yanqing Zhang,et al.  Statistical fuzzy interval neural networks for currency exchange rate time series prediction , 2007, Appl. Soft Comput..

[6]  Marcelo C. Medeiros,et al.  Modeling exchange rates: smooth transitions, neural networks, and linear models , 2001, IEEE Trans. Neural Networks.

[7]  Kimon P. Valavanis,et al.  Surveying stock market forecasting techniques - Part II: Soft computing methods , 2009, Expert Syst. Appl..

[8]  Kemal Kilic,et al.  Comparison of Different Strategies of Utilizing Fuzzy Clustering in Structure Identification , 2007, Inf. Sci..

[9]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[10]  Paolo Tenti,et al.  Forecasting Foreign Exchange Rates Using Recurrent Neural Networks , 1996, Appl. Artif. Intell..

[11]  Yungho Leu,et al.  A distance-based fuzzy time series model for exchange rates forecasting , 2009, Expert Syst. Appl..

[12]  Arie Preminger,et al.  Forecasting Exchange Rates: A Robust Regression Approach , 2005 .

[13]  Joarder Kamruzzaman,et al.  ANN-Based Forecasting of Foreign Currency Exchange Rates , 2004 .

[14]  Francesco Lisi,et al.  A comparison between neural networks and chaotic models for exchange rate prediction , 1999 .

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

[16]  Hiok Chai Quek,et al.  GA-TSKfnn: Parameters tuning of fuzzy neural network using genetic algorithms , 2005, Expert Syst. Appl..

[17]  Michio Sugeno,et al.  A fuzzy-logic-based approach to qualitative modeling , 1993, IEEE Trans. Fuzzy Syst..

[18]  Chuen-Tsai Sun,et al.  Functional equivalence between radial basis function networks and fuzzy inference systems , 1993, IEEE Trans. Neural Networks.

[19]  E. Fama.  The Behavior of Stock-Market Prices , 1965 .

[20]  E. Mizutani,et al.  Levenberg-Marquardt method for ANFIS learning , 1996, Proceedings of North American Fuzzy Information Processing.

[21]  K. Maertens,et al.  Genetic polynomial regression as input selection algorithm for non-linear identification , 2006, Soft Comput..

[22]  Robert Babuska,et al.  Neuro-fuzzy methods for nonlinear system identification , 2003, Annu. Rev. Control..

[23]  Kiyoshi Izumi,et al.  Phase transition in a foreign exchange market-analysis based on an artificial market approach , 2001, IEEE Trans. Evol. Comput..

[24]  Giovanna Castellano,et al.  A fuzzy clustering approach for mining diagnostic rules , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[25]  Mohammad Teshnehlab,et al.  Novel Hybrid Learning Algorithms for Tuning ANFIS Parameters as an Identifier Using Fuzzy PSO , 2008, 2008 IEEE International Conference on Networking, Sensing and Control.

[26]  P ValavanisKimon,et al.  Surveying stock market forecasting techniques - Part II , 2009 .

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

[28]  An-Sing Chen,et al.  Regression neural network for error correction in foreign exchange forecasting and trading , 2004, Comput. Oper. Res..

[29]  Ganapati Panda,et al.  Efficient prediction of exchange rates with low complexity artificial neural network models , 2009, Expert Syst. Appl..