Exchange rate forecasting using classifier ensemble

In this paper, we investigate the impact of the non-numerical information on exchange rate changes and that of ensemble multiple classifiers on forecasting exchange rate between U.S. dollar and Japanese yen. We first engage the fuzzy comprehensive evaluation model to quantify the non-numerical fundamental information. We then design a single classifier, addressing the impact of exchange rate changes associated with this information. In addition, we also propose other different classifiers in order to deal with the numerical information. Finally, we integrate all these classifiers using a support vector machine (SVM). Experimental results showed that our ensemble method has a higher degree of forecasting accuracy after adding the non-numerical information. © 2009 Springer-Verlag Berlin Heidelberg.

Duke Scholars

Author Kaizhu Huang DKU Faculty