Forecasting exchange rate using support vector machines
Authors:
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6 (2160133X) , 3448
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.Keywords
This publication has 8 references indexed in Scilit:
- Evolving RBF neural networks for time-series forecasting with EvRBFInformation Sciences, 2004
- Financial time series forecasting using support vector machinesNeurocomputing, 2003
- Improved financial time series forecasting by combining Support Vector Machines with self-organizing feature mapIntelligent Data Analysis: An International Journal, 2001
- Application of support vector machines in financial time series forecastingOmega, 2001
- A case study on using neural networks to perform technical forecasting of forexNeurocomputing, 2000
- An Introduction to Support Vector Machines and Other Kernel-based Learning Methods2000
- A comparison between neural networks and chaotic models for exchange rate predictionComputational Statistics & Data Analysis, 1999
- Comparing the forecasting performance of neural networks and forward exchange ratesJournal of Multinational Financial Management, 1997