Application of Support Vector Machines in Financial Time Series Forecasting

Because the financial time series are inherently noisy,non-stationary and deterministicaUy chaotic, it is difficult to describe this system by traditional methods.The authors presented a novel load forecasting method i.e.an improved Support Vector Machines(SVM).The object of this paper is to examine the feasibility of SVM in financial time series forecasting by comparing it with a back-propagation(BP)neural network.Analysis of the experiment results proves that it is advantageous to apply SVMs to forecast fmancial time series.