Support vector regression based approach for key index forecasting with applications

• Published in: IEEE International Conference on Industrial Informatics (INDIN) pp. 591 - 596
• Main Authors: Shen Yin, Fang Wu, Hao Luo, Huijun Gao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2015
• Subjects: Accuracy; Birds; Data models; Forecasting; Indexes; Least squares support vector machine; Particle swarm algorithm; Prediction algorithms; Real-time monitoring; Support vector machine regression; Support vector machines
• ISSN: 1935-4576
• DOI: 10.1109/INDIN.2015.7281800

With the rapid development in science and technology, data acquisition, storage and mining technology are widely applied to various fields. All aspects of people's lives are recorded as data. Through the analyzing and arranging of data, people can get a lot of valuable information. In this paper, support vector machine (SVM), least squares support vector machine (LSSVM) and partial least squares (PLS) are respectively used in the field of economic research. Real-time monitoring and forecasting for stock index is vital to the market. The changing trend and index of stocks are predicted according to the analysis to the history data of the stock. By combining particle swarm algorithm (PSO) algorithm and LSSVM algorithm, the parameters in the LSSVM model can be optimized. These algorithms are compared on the basis of their forecasting results.