Stock price forecasting using a hybrid ARMA and BP neural network and Markov model

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.