Research On Prediction Of Second-Hand House Prices In Beijing Based On Combination Model

The real estate industry is the leading industry of China’s national economy and plays a pivotal role in social and economic life.Among them,the second-hand housing market in real estate plays an important role in the overall stable and healthy development of the real estate market.However,the reasons affecting the housing price of second-hand housing are complex,especially unexpected events such as policies have a profound impact on housing prices,resulting in a huge amount of information that needs to be processed in the forecasting modeling of housing prices at this time.How to predict the changing trend of housing prices in second-hand housing more accurately is the key It has always been a crucial topic,and it has a great auxiliary effect on home buyers,real estate developers and the government.This thesis takes second-hand housing in Beijing as an example to study the impact of policies on the Beijing housing market and how to predict housing prices.Based on reviewing and sorting out the time series interference model and neural network model,this thesis combines the interference analysis model with BP neural network,and conducts an empirical study using the average housing price data of ordinary second-hand houses in Beijing.This thesis first builds a regression model on the data of second-hand housing prices in Beijing before the policy,and then performs interference prediction model fitting prediction on the housing prices of second-hand housing in Beijing after the policy.Secondly,build a BP neural network model for it,and perform neural network parameter selection and extrapolation prediction.Finally,after optimization and improvement,the combination model analysis of the interference analysis model and the BP neural network model was completed,and a rigorous empirical analysis was carried out to explore the impact of the policy on the secondhand housing market in Beijing,and the impact on the second-hand housing in Beijing after the policy occurred.House prices are forecasted.In this thesis,the combination model of the intervention analysis model and the BP neural network model is used to predict the house price of second-hand housing.The test proves that the combination model is better than the single interference analysis model or the BP neural network prediction effect in terms of policy impact and prediction on housing prices.In the future The combined model can be applied to the housing price prediction of other cities and other fields.