Early Warning System Research Based On Bp Neural Network

Real estate development is not only related to the living standard and living conditions of the urban residents, but also can reflect a country or region's political and economic situation. In particular, in our country, after years of booming development, real estate industry has become a pillar industry of China's national economy. The real estate industry has made great achievements, but we also should see some notes of discord——blind development,vicious speculation, and so large number of vacant. There are "overheating theory" and "bubble theory" appeared on the market. One of the most important reasons of China's overheated real estate development is the lack of research and practice of early warning system. However, the nonlinear characteristics of the real estate market made the market simulation became more difficult.Therefore, the purpose of this paper is to solve the problem of nonlinear real estate market, establishing a complete and effective early warning system for the earl estate market, and provide the protection for the healthy and stable development of China's real estate industry.This paper selected BP neural network model to build the real estate early warning system. This paper integrated and optimized the sub-factor weights on aspects of development, harmony and risk in a systematic way, and choused 13 warning signs of the real estate market indicators. Then, this paper collected Wuhan indicator data in recent years and did empirical research. With the help of Matlab 7.0 toolbox of artificial neural network programming, this paper trained the neural network, and got a practical net. Through testing, the BP neural network model established in this paper has good generalization ability, it can make accurate judgments. On this basis, this paper predicted the real estate in Wuhan to run a "normal" state in 2010. Finally, this paper made some recommendations to ptrent overheating of the real estate market development in Wuhan.