INTERNATIONAL RESEARCH JOURNAL OF SCIENCE ENGINEERING AND TECHNOLOGY

( Online- ISSN 2454 -3195 ) New DOI : 10.32804/RJSET

Impact Factor* - 6.2311


**Need Help in Content editing, Data Analysis.

Research Gateway

Adv For Editing Content

   No of Download : 27    Submit Your Rating     Cite This   Download        Certificate

AN ENSEMBLE APPROACH FOR EXCHANGE RATE FORECASTING USING MULTIVARIATE DATA

    3 Author(s):  MRS.RESHMA. K.S, DR. R.SUNDER, DR.M.RAJESWARI

Vol -  10, Issue- 2 ,         Page(s) : 149 - 154  (2020 ) DOI : https://doi.org/10.32804/RJSET

Abstract

A Cluster based Nonlinear Ensemble(CNE) approach for exchange rate forecasting using multivariate data, This approach uses Vector AutoRegression(VAR), Artificial Neural Network(ANN), Self Organizing Map(SOM) and, Kernel based Extreme Learning Machine(KELM). Foreign exchange rate is dynamic and volatile and depends on many factors like inflation, interest rate, government debt, unemployment rate etc. So to consider this type of data, this approach uses multivariate data for more accurate exchange rate prediction. In this CNE approach, also consider economic indicators Inflation and interest rate. The ensemble approach result shows better performance than component forecast models.

[1] Shaolong Sun , Shouyang Wang, Yunjie Wei, and Guowei Zhang, “A Clustering-Based Nonlinear Ensemble Approach for Exchange Rates Forecasting”, Ieee transactions on systems, man, and cybernetics: systems,  pp. 2168-221, 2018.
[2] J. M. Bates and C. W. J. Granger, “The combination of forecast, Operational               research quarterly”, vol. 20 no. 4, 2016. 
[3] A. Moosa and J. J. Vaz, “Cointegration, error correction and exchange rate              forecasting”, J. Int. Financ. Mark. Inst. Money, vol. 44, pp. 21–34, Sep, 2016  
[4] M. McCrae, Y.-X. Lin, D. Pavlik, and C. M. Gulati, “Can cointegration- based               forecasting outperform univariate models? An application to Asian exchange rates”, J.           Forecast., vol. 21, no. 5, pp. 355–380, 2002. 
[5] N. L. Joseph, “Model specification and forecasting foreign exchange rates with             vector autoregressions, J. Forecast”, vol. 20, no. 7, pp. 451–484, 2001.  
[6] R. A. Meese and K. Rogoff, “Empirical exchange rate models of the seventies:               Do they t out of the sample”,  J. Int. Econ., vol. 14, nos. 1–2, pp. 3–24, 1983. 
[7] L. Yu, K. K. Lai, and S. Wang,  “Multistage RBF neural network ensem- ble                learning for exchange rates forecasting, Neurocomputing”, vol. 71, nos. 16–18, pp.           3295–330, 2008.  
[8] K. S. Rogoff and V. Stavrakeva, “The continuing puzzle of short hori- zon               exchange rate forecasting”,  NBER, Cambridge, MA, USA, Working Paper Series, 2008. 
[9] Omolbanin Yazdanbakhsh, “Forecasting of Multivariate Time Series via          Complex Fuzzy Logic, Ieee transactions on systems, man, and cybernetics: systems”, pp.            2168-2216, 2016.   
[10] G. Sermpinis, C. Dunis, J. Laws, and C. Stasinakis, “Forecasting and trading              the EUR/USD exchange rate with stochastic neural network com- bination and           time-varying leverage”, Decis. Support Syst., vol. 54, no. 1, pp. 316–329, 2012.    
[11] D. E. Rapach and M. E. Wohar, “The out-of-sample forecasting performance of              nonlinear models of real exchange rate behavior”, Int. J. Forecast., vol. 22, no. 2, pp.               341–361, 2006.  
[12] Lara Khansa, Divakaran Lijinlal, “Predicting stock market returns: A           comparative study of vector autoregression and time delayed neural network”, Decis.           Support Syst., vol. 51,  pp. 745–759, 2011. 

*Contents are provided by Authors of articles. Please contact us if you having any query.






Bank Details