Research On The Valuation Model Of Second-hand Housing In Beijing Based On Functional Data

The real estate industry has an important position in China's economic development system due to its huge financing amount,long industrial chain and important connection with all aspects of the social economy.At present,economic development has promoted people's social demand,and the number of new houses is limited,so China's housing market has changed from new house market to second-hand house market.Therefore,accurate and comprehensive second-hand house appraisal provides buyers and sellers with scientific appraisal price,and effectively promotes real estate transaction business.This paper USES the traditional statistical model and the functional principal component regression model to evaluate the real estate price.This paper takes the price evaluation model of second-hand housing in Beijing as an example to study.Firstly,the data of second-hand housing sales in 11 major urban areas of Beijing from2015 to 2019 were crawled from the HOME LINK website by using web crawler technology.In order to improve the accuracy of the model and reduce the complexity of the model,the variables with little impact on the housing price were removed,and the optimal indicator system was finally selected.Secondly,the functional regression model based on functional principal component analysis was used to evaluate the price of second-hand houses in Beijing,and the model parameters were adjusted reasonably to obtain the optimal model.The model was applied to the test data for prediction,and the model error was obtained,so as to judge the rationality of the model.Finally,the functional regression model based on functional principal component analysis is compared with linear regression model and random forest model.The final results show that the functional regression model based on functional principal component analysis has less prediction error and higher model stability,which is a method worthy of promotion in real estate evaluation.