Forecasting exchange rate using support vector machines

Authors:

Abstract
Recently, support vector machines is a focus research field in the world, support vector regression which is used as a technology to solve the regression problems have the advantages of global optimal solutions, the solutions avoiding overtraining and so on. This paper establishes a model of exchange rate prediction based on support vector machines, collects the daily data of USD/GBP exchange rate and uses these data to train the model and checks the predictive power of this model. The result shows that SVM model has some predictive power; it can be used to forecast finance time series. In addition, this article also discusses the issue on finding the optimal parameters of SVM and does lots of experiments to find them.

This publication has 8 references indexed in Scilit: