基于梯度提升回归树模型的上海市二手房均价分析

Analysis of the Average Price of Second-Hand Houses in Shanghai Based on Gradient Boosting Regression Tree

摘要: 本文基于梯度提升回归树集成模型，利用采集的“链家”网站上海市近三年各住宅小区二手房的相关数据，分析影响上海市二手房均价的因素。对各影响因素运用Person相关系数矩阵及热力图进行初步分析，并将收集的数据分为训练集和测试集，训练并测试支持向量机模型、线性回归模型及集成模型。最终实验结果表明，基于梯度提升回归树的集成模型更能准确的预测上海市二手房的均价，且梯度提升回归树的MSE是其中最小，相关系数最大达到0.831，具有较好的拟合效果。

Abstract: Based on the gradient boosting regression tree, we analyze the factors affecting the average price of second-hand houses in Shanghai by using the data collected from “HOME LINK” website in recent three years. The Person correlation coefficient matrix and heat map are used for preliminary analysis of each influencing factor. Moreover the collected data are divided into training set and test set, and the support vector machine model, linear regression model and integration model are trained and tested respectively. The final experimental results show that the integrated model based on gradient boosting regression tree can more accurately predict the average price of second-hand houses in Shanghai. And the MSE of gradient boosting regression tree is the smallest, furthermore the correlation coefficient is up to 0.831, which has the best fitting effect.