Research On Second-hand Housing Price Prediction In Nanjing Based On Machine Learning Model

The study of housing price has always been a hot topic pursued by many scholars,and scholars are trying to find the reasons behind the rise and fall of housing prices from different perspectives,so as to lay a foundation for the prediction of the future trend of housing prices.There are many factors affecting the housing price,and the influence mechanism is becoming more and more complex.It is difficult to accurately achieve the housing price forecast.The rapid breakthrough of machine learning algorithm and artificial intelligence makes the housing price prediction achieve a more balanced result under certain set conditions.Therefore,this paper will build a sufficient and stable algorithm environment,based on the application of machine learning algorithm in the Nanjing second-hand housing price prediction,through the prediction model to achieve the Nanjing second-hand housing transaction price forecast,and the prediction accuracy and accuracy comparison evaluation.From the macro and micro dimension,this thesis is committed to explore the factors of Nanjing secondary housing price rise and fall,and through different machine learning prediction model,such as multiple regression,gray prediction model,BP neural network and the random forest algorithm,and the prediction accuracy is low,and the neural network model in the near years,the older the prediction accuracy of the year,and the random forest model,the prediction accuracy is higher and higher.Through this article about Nanjing second-hand housing price forecast,hope to bring Nanjing second-hand housing buyers beneficial realistic guidance,make potential buyers can reasonable evaluation of the second-hand housing price value,and according to their own needs to find the best cost-effective house,and the government regulators to develop effective regulation policy to provide reference.