Research on Prediction Methods of Residential Real Estate Price Based on Improved BPNN

To improve the prediction precision of residential property, the paper brings up a mixed optimizing model based on IPSO-BPNN. The model has adopted gray correlation theory to optimized the the index that influences price and use IPSO to optimize the definition of original weights and threshold value. We take the real estate market in Changsha as an example. The result shows that the speed of convergence and prediction precision of this method is superior to traditional BP neural network and IPSO-BPNN. This optimizing algorithm overcomes the drawbacks of neural network and particle swarm optimizing method, and improves the speed of convergence and the ability of searching optimum value globally.