Analysis And Forecast Of Housing Price In Qingdao

Buying and selling a house has always been the biggest concern of the people,and it is a matter of great importance to people's livelihood.However,the rising housing prices has always puzzled most of the middle and low-income groups in China,and it has become a sensitive issue in people's daily life.Therefore,studying the influencing factors of real estate prices and making predictions will help the middle and low-income groups choose the right time to buy a house and also can help the government-related personnel understand the trend of real estate prices and regulate its prices.This paper takes the housing price of Qingdao as an example,according to the model of principal component regression analysis,seven factors that include most of the information about the housing price of Qingdao are obtained,they are the city's GDP,local fiscal revenue,local fiscal expenditure,disposable income of urban and rural residents,real estate development investment,consumer price index,fixed asset investment price index,sales area of commercial housing and the completed area of residential buildings in the whole society.On this basis,a multiple nonlinear regression model and a neural network model for the above seven indicators are established respectively,and then are used to analyze and predict.The same conclusions are concluded that the sales price of commercial housing in Qingdao has an upward trend in 2018.Finally,the time series model is used to analyze and predict the sales price of commercial housing in Qingdao.The time series model only starts from the index of residential sales price in Qingdao city,the trend of Qingdao house prices from January 2019 to February 2020 is predicted,the conclusions are: the house prices will still rise in the first four months of 2019,and it will have a sharp downward trend from April 2019 to October 2019 and then will have a slow downward trend from October 2019 to February 2020.These are basically the same as the reality,so the prediction effect of time series models is better than other models.