Stock Price Forecasting Based on Dynamic Factor Augmented Model Averaging Approach

Abstract

Accurate forecasting of stock prices not only guides investor behavior but also assesses financial risk and promotes balanced economic and social development. This paper uses a dynamic factor-enhanced model averaging method to forecast the daily closing price of the Shanghai Composite Index, maximizing the use of valid information by weighting the forecast values of different models. Firstly, the common factor is extracted from the smoothed original explanatory variables; then the dynamic factor augmented model selection method and the model averaging method based on different criteria are used to predict different lag orders of the common factor and the explanatory variables, and the effectiveness of the dynamic factor augmented censored group cross-validation model averaging method is verified using multiple predictor error indicators as well as the DM test. The experimental results show that the dynamic factor augmented censored group cross-validation model averaging method has better prediction results and is more robust.