Hits:

Indexed by:会议论文

Date of Publication:2012-11-09

Included Journals:EI、CPCI-S、Scopus

Page Number:981-985

Key Words:stock price forecasting; ARMA; BPNN; Markov model

Abstract:Stock price forecasting is a very important financial topic and it is of great importance to both market economy and investors. Stock price series is complex, nonlinear and dynamic that it's difficult to predict it effectively by a single method. This paper proposes a hybrid method combining autoregressive and moving average (ARMA), back propagation neural network (BPNN) and Markov model to forecast the stock price. ARMA and BPNN solve the linear and nonlinear component of the stock price series respectively and Markov model can modify the result to be better. The experimental result shows that the proposed method can improve forecasting accuracy.