International Journal of Economics and Business Administration
Articles Information
International Journal of Economics and Business Administration, Vol.2, No.5, Sep. 2016, Pub. Date: Nov. 2, 2016
Hybrid Particle Swarm Optimization and Support Vector Regression Performance in Exchange Rate Prediction
Pages: 59-64 Views: 717 Downloads: 466
[01] Feng Jiang, School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, China.
[02] Wenjun Wu, School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, China.
In this paper, we present a hybrid particle swarm optimization and support vector regression approach to predict exchange rate. This hybrid method examines the validity to optimize the parameters of penalty term and kernel function. For the experiments, the data of exchange rates (USD/CNY, EUR/CNY and CNY/JPY) are examined and optimized to be used for time series predictions with hybrid particle swarm optimization and support vector regression. Some experiments have been analyzed by using the hybrid regression model with four kernel functions including linear, radical basis, polynomial and sigmoid functions. The in-sample and out-of-sample results are compared with training ones. Empirical results show that the hybrid model has high accuracy and it is statistically effective for CNY exchange rate prediction.
Particle Swarm Optimization, Support Vector Regression, Exchange Rate
[01] Cortes, C., V. Vapnik (1995). Support-vector networks, Machine Learning, 20, 273-297.
[02] Kwon, Y., B. R. Y. K. Moon (2007). A hybrid neurogenetic approach for stock forecasting, IEEE Trans. Neural Netw., 18, 851-864.
[03] Ince, H., T. Trafalis (2006). A hybrid model for exchange rate prediction, Decision Support Systems, 42, 1054-1062.
[04] Brandl, B., U. Wildburger, S. Pickl (2009). Increasing of the fitness of fundamental exchange rate forecast models, International Journal of Contemporary Mathematical Sciences, 4, 779-798.
[05] Rubio, G., H. Pomares, I. Rojas, L. Herrera (2011). A heuristic method for parameter selection in LS-SVM: application to time series prediction, International Journal of Forecasting, 27, 725-739.
[06] Sermpinis, G., C. Stasinakis, K. Theofilatos, A. Karathanasopoulos (2015). Modeling, forecasting and trading the EUR exchange rates with hybrid rolling genetical gorithms—Support vector regression forecast combinations, Euro. J. Oper. Res., 247, 831–846.
[07] Dunis, C., M. Williams (2002). Modeling and trading the EUR/USD exchange rate: do neural network models perform better?, Derivatives Use, Trading and Reg., 8, 211–239.
[08] Bissoondeeal, R., M. Karoglou, A. M. Gazely (2011). Forecasting the UK/US exchange rate with divisia monetary models and neural networks, Scott. J. Political Econ., 58, 127–152.
[09] Abraham, A., A. Yeung (2003). Integrating ensemble of intelligence systems for stock exchange prediction, Notes on Computational Science, 2687, 774-781.
[10] Härdle, W., W. Lee, D. Schäfer, Y. Yeh (2009). Variable selection and oversampling in the use of smooth support vector machines for predicting the default risk of companies, Journal of Forecasting, 28, 512-534.
[11] Sapankevych, N., R. Sangar (2009). Time series prediction using support vector machines: a survey, IEEE Computational Intelligence Magazine, 4, 24-38.
[12] Khandani, A., A. Kim, A. Lo (2010). Consumer credit-risk models via machine-learning algorithms, J. Bank. Finance, 34, 2767-2787.
[13] Öğüt, H., Doğanay, M., Ceylan, N., Aktaş R. (2012). Prediction of bank financial strength ratings: the case of Turkey, Economic Modelling, 29, 632-640.
[14] Papadimitriou, T., P. Gogas, M. Matthaiou, E. Chrysanthidou (2015). Yield curve and recession forecasting in a machine learning framework, Computational Economics, 45, 635-645.
[15] Sadaei H. J., Enayatifar R., Guimaraes, F. G., Mahmud M., Alzamil, Z. A. (2016). Combining ARFIMA models and fuzzy time series for the forecast of long memory time series, Neuralcomputing, 175, 782-796.
[16] Deng W. H., Wang G. Y., Zhang X. R., Xu J., Li G. D. (2016). A multi-granularity combined prediction model based on fuzzy trend forecasting and particle swarm techniques, Neuralcomputing, 173, 1671-1682.
[17] Cheng S., Chen S., Jian W. (2016). Fuzzy time series forecasting based on fuzzy logical relationships and similarity measures, Information Sciences, 327, 272-287.
[18] Chen S., Chen S. (2015). Fuzzy Forecasting Based on Two-Factors Second-Order Fuzzy-Trend Logical Relationship Groups and the Probabilities of Trends of Fuzzy Logical Relationships, IEEE Transactions on Cybernetics, 45, 405-415.
[19] Chen Shyi-Ming, Manalu Gandhi Maruli Tua, Pan Jeng-Shyang, Liu Hsiang-Chuan (2013) Fuzzy Forecasting Based on Two-Factors Second-Order Fuzzy-Trend Logical Relationship Groups and Particle Swarm Optimization Techniques, IEEE Transactions on Cybernetics, 43, 1102-1117.
[20] Chen M. (2012). A Hybird Model for Business Failure Prediction- Utiliazation of Particle Swarm Optimizaition and Support Vector Machines, Neural Network World, 21, 129-152.
[21] Chen M. (2014). Using a hybrid evolution approach to forecast financial failures for Taiwan-listed companies, Quantitavie Finance, 14, 1047-1058.
MA 02210, USA
AIS is an academia-oriented and non-commercial institute aiming at providing users with a way to quickly and easily get the academic and scientific information.
Copyright © 2014 - 2017 American Institute of Science except certain content provided by third parties.