An improved method of support vector machine and its applications to financial time series forecasting

作者：Liang YC^*; Sun YF

来源：Progress in Natural Science, 2003, 13(9): 696-700.

DOI：10.1080/10020070312331344260

• support vector machine (SVM)
• data-dependent
• information geometry
• conformal mapping
• financial time series
• stock price prediction

A novel method for kernel function of support vector machine is presented based on the information geometry theory. The kernel function is modified using a conformal mapping to make the kernel data-dependent so as to increase the ability of predicting high noise data of the method. Numerical simulations demonstrate the effectiveness of the method. Simulated results on the prediction of the stock price show that the improved approach possesses better forecasting precision and ability of generalization than the conventional models.

• 出版日期2003-9
• 单位吉林大学