基于多源数据的武汉房价时空模式与驱动机制研究

Research on Spatio-temporal Patterns and Driving Mechanisms of House Prices in Wuhan Based on Multi-source Data

近年来城市房价时空变化剧烈,时空模式和驱动机制研究意义显著。本文基于大数据分析武汉主城区房价的时空特征与演变模式,基于地理加权回归模型(GWR)挖掘影响因素的驱动机制。研究表明:房价时空模式呈多中心结构,2012―2018年演化为“簇团+圈层+扇形”交互并存的混合模式,房价总体提升,高档住宅区集聚蔓延,副中心迅速崛起,时空发展不均衡,方向差异性显著;房价驱动机制结果说明同一因素在不同区位作用力差异显著,多因素共同影响房价,公园、景观、义务教育优势对高档住宅区作用显著提升,且等级决定作用力强弱,交通、中心优势对外围住宅的增值效率加强。研究结果可为城市房价时空模式、社会分异研究提供新的参考视角。

In recent years,urban housing prices have changed dramatically in time and space,and the research of their spatio-temporal patterns and driving mechanisms is of great significance.This study is based on big data analysis to capture the spatio-temporal characteristics and evolution mode of housing prices in the main urban area of Wuhan,and to explore the driving mechanism of influencing factors based on the geographic weighted regression model(GWR).The research results show that:the spatio-temporal pattern of house prices is polycentric,evolving into a mixed pattern of “cluster+circle+sector” from 2012 to 2018,with an overall increase in house prices,the "clustering and spreading" of high-grade residential areas,the rapid rise of sub-centers,uneven spatio-temporal development and significant differences in direction.The results of the house price driving mechanism show that the same factor has significant differences in the force of action in different locations,and multiple factors jointly influence house prices,the advantages of parks,landscapes and school districts have significantly enhanced the role of high-grade residential areas,and the rank determining the strength of the force,the value-added efficiency of transportation and central advantages for peripheral residences strengthening.This study provides a new perspective for the study of spatio-temporal patterns of urban housing prices and social differentiation.