Forecasting Model of Chinese Stock Index by Stochastic Time Effective Neural Network

Abstract

In this paper, we investigate the statistical properties of fluctuations of Chinese stock index. According to the theory of artificial neural network, a stochastic time effective function is introduced in the forecasting model of the index in the present paper, which gives an improved neural network - the stochastic time effective neural network model. In this model, a promising data mining technique in machine learning has been proposed to uncover the predictive relationships of numerous financial and economic variables. We suppose that the investors decide their investment positions by analyzing the historical data on the stock market, and the historical data is given a weight depending on it's time, in details that, the nearer the time of the historical data is to the present, the stronger impact the data has on the predictive model, and we also use the probability density functions to classifying the various variables from training samples. In the last part of the paper, the data of 16 years' period of Shenzhen stock index is analyzed in the stochastic time effective neural network model, and we show some analysis results for the fluctuations of the index by the model.