Abstract
Support vector machines (SVMs) are promising methods for the prediction of financial time-series because they use a risk function consisting of the empirical error and a regularized term which is derived from the structural risk minimization principle. This study applies SVM to predicting the stock price index. In addition, this study examines the feasibility of applying SVM in financial forecasting by comparing it with back-propagation neural networks and case-based reasoning. The experimental results show that SVM provides a promising alternative to stock market prediction.
Original language | English |
---|---|
Pages (from-to) | 307-319 |
Number of pages | 13 |
Journal | Neurocomputing |
Volume | 55 |
Issue number | 1-2 |
DOIs | |
State | Published - Sep 2003 |
Keywords
- Back-propagation neural networks
- Case-based reasoning
- Financial time series
- Support vector machines