Research On The Application Of Chaotic Time Series Prediction

Nonlinear science to flourish in recent years was almost involved in the natural and social sciences in various fields. Forecast the evolution of complex systems development has become a research hotspot, it has a wide range of applications. The traditional model of chaotic time series prediction is usually divided into two categories: dynamics method based on nonlinear mathematical model and phase space reconstruction method based on the actual observation data. In this paper, the second forecast method is used.Reconstitution of phase space and computation of geometrical eigenvalues are important processes in chaotic dynamical analysis. This paper studies the choice of chaotic time series phase space reconstruction parameters and chaotic time series forecasting methods. This paper constructs BP neural network prediction model, has improved BP neural network prediction model by using genetic algorithms (GA-BP) and constructs least squares support vector machine prediction model. This paper makes a comparative analysis about the Lorenz chaotic system model; Article confirmed that GA-BP meets basic demand of prediction accuracy. A large number of studies have shown that fluctuations of China's stock market have chaotic characteristics; prediction is feasible in short time. Therefore GA-BP is used to forecast the daily turnover of the Shanghai stock market; the results confirm the validity of this prediction method.