Forecast Research Of Real Estate Price Index Based On WNN

By observing the movement of Real estate price index, people can grasp of the macro economic situation of the real estate market and the changes in the market, or from the micro level, people also can take an analysis according its investment trend, and the realization of these roles based on the analysis and forecast of real estate price index. In recent years, with the real estate market continued to heat up, problems about the risk of the real estate industry have become increasingly prominent. Using scientific methods to reflect the changes in real estate prices, and presenting a correct information guide to the main market has become very urgent.Because the real estate price index frequently manifests nonlinear in itself, so it must be forecast by using a model which can simulate nonlinear. In theory, neural network can unlimited approximate nonlinear function, but the traditional error of the back-propagation algorithm multilayer feed-forward network (BP neural network), there are the flaws of a slow convergence of forecast, getting local minimum solutions easily, and forecast accuracy rate is not high. Wavelet analysis is a new theory, which overcomes the shortcomings of traditional Fourier analysis, has good localized characteristics in the time domain and frequency domain, and has important value. in signal processing, image processing, voice analysis and other fields. In the previous chapters of this paper, will introduce the real estate price index theory, wavelet analysis theory and neural network theory; And in the last several chapters, will improve the BP neural network, will combine it with wavelet analysis and establish a new model—wavelet neural network model(WNN).Train and simulate the selected data by WNN, and forecast by the finished network, then compare the forecast results with the true values to reduce error, at last, compare with the simple use of BP neural network to predict, find that the WNN forecast could overcome the flaws of BP neural network , and achieve better results. In the final article of the paper, show the shortage of the research and has a prospect for the future of the WNN research.