Early Warning System Research Based On BP Neural Networks For Xi'an Real Estate Market

Real estate is an important part of national economy, which has cycling characteristics. Too large fluctuation contradicts with the continuing healthy and stable development of the real estate economy. At the same time, as a subsystem of the society economy system, real estate has non-linear complex traits. The purpose of this article is: in order to prevent the real estate economy from the nonnormal fluctuation and keep it developing healthy and stable, through establishing an advanced and scientific early warning system based on nonlinear real estate system.Against this background, the thesis gets the idea of building the early warning system based on artificial neural network into shape firstly started with the economy early warning theory and business fluctuation theory. Next, it makes Xian as the empirical study, and the date from 1997 which is related to real estate was collected in Xian. As a result, 9 samples are obtained from these data. On the next step, a program realizing the training of artificial neural network is compiled in the thesis by the neural network box of Matlab 7.1, and the early warning model of real estate market is built by training the samples. Testing result indicates that the model built in the thesis is qualified for the early warning of real estate market. the thesis analyzes the Xian real estate market by the early warning model based on the artificial neural network, output of the model indicate that the Xian real estate market of 2006 will on the degree of "hot". At last, we raised some policy proposals for the actual about Xi'an real estate market.