Forecasting Method of Stock Price Based on Polynomial Smooth Twin Support Vector Regression

摘要

The stock price prediction has become an important research topic in Economics. However, the traditional forecasting methods only can be used in linear system, whose prediction accuracy is not satisfactory. In this paper, a new forecasting method of stock price based on polynomial smooth twin support vector regression is proposed. In the proposed method, we firstly construct the polynomial smooth twin support vector regression (PSTSVR) model and prove its global convergence. Then PSTSVR is used as the opening price of stock prediction model. The experimental results on the stock data from the great wisdom stock software show that the proposed method can obtain the better regression performance compared with SVR and twin support vector regression (TSVR).