Authors:
Minghao Zhu
and
Jie Li
Affiliation:
Beijing Jiaotong University, China
Keyword(s):
Stock index, Mutual prediction, Nonlinear dependence, Support Vector Machine.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence and Decision Support Systems
;
Enterprise Information Systems
;
Parallel Control and Management in ITS
Abstract:
China's market economy continues to advance, which makes the transparency of information of stock market increasing, the information between the stock market flows faster, a variety of interactions between the stocks increasingly significant. In this paper, support vector machine method is used to study the stock market in the nonlinear discontinuous time series, through the establishment of different support vector machine model, respectively to predict for the Shanghai A shares index, the Shenzhen A share index, the Shanghai B share index and Shenzhen B share index, analyze their absolute error and relative error, it was found there is a strong nonlinear interdependence in the same stock market and a strong dependence of different securities markets, the Shanghai index has a larger effect compare to the Shenzhen index slightly.