Combining wavelet-based feature extractions with SVMs for financial time series forecasting

Abstract

Support vector machine (SVM) has appeared as a powerful tool for time series forecasting and demonstrated better performance over other methods. This paper proposes a novel hybrid model which combines wavelet-based feature extractions with SVM models for stock index forecasting. The time series of explanatory variables are decomposed by the wavelet basis, and the extracted time-scale features then serve as inputs of a SVM model which performs the nonparametric forecasting. Compared with pure SVM models or traditional GARCH models, the performance of the new method is the best. The root-mean-squared forecasting errors are significantly reduced. The results of this study can help investors for controlling and reducing their risks in international investments.

Keywords and phrases:

• Support vector machine
• wavelet analysis
• time series forecasting
• feature extraction
• hybrid forecasting