Spatiotemporal Analysis of Housing Prices in China: A Big Data Perspective

• Published in: Applied spatial analysis and policy Vol. 10; no. 3; pp. 421 - 433
• Main Authors: Li, Shengwen, Ye, Xinyue, Lee, Jay, Gong, Junfang, Qin, Chenglin
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.09.2017; Springer Nature B.V
• Subjects: Big Data; Case studies; Economic development; Economic growth; Economic research; Fluctuations; Housing; Housing prices; Human Geography; Internet; Landscape/Regional and Urban Planning; Migration; Predictions; Prices; Property; Real estate; Real estate sales; Regional/Spatial Science; Rural areas; Social Sciences; Spacetime; Spatial analysis; Spatial distribution; Trends; Urbanization; China; Space-time; Big data; Housing price; China
• ISSN: 1874-463X; 1874-4621
• DOI: 10.1007/s12061-016-9185-3

Due to the rapid economic growth and urbanization, China’s real estate industry has been undergoing a fast-paced development in recent decades. However, the spatial imbalance between the economic growth in urban and that in rural areas and the excessive growth and fluctuations of house prices in both areas had quickly caught public’s attention. Not surprisingly, these issues had become a focus of urban and regional economic research. Efficient and accurate prediction of housing prices remains a much needed but disputable topic. Currently, based on the trends and changes in the financial market, population migration and urbanization processes, numerous case studies have been developed to evaluate the mechanism of real estate’s price fluctuations. However, few studies were conducted to examine the space-time dynamics of how housing prices fluctuated from a big data perspective. Using data from China’s leading online real estate platform {sofang.com}, we investigated the spatiotemporal trends of the fluctuations of housing prices in the context of big data. This paper uses spatial data analytics and modeling techniques to: first, identify the spatial distribution of housing prices at micro level; second, explore the space-time dynamics of residential properties in the market; and third, detect if there exist geographic disparity in terms of housing prices. Results from our analysis revealed the space-time patterns of the housing prices in a large metropolitan area, demonstrating the utility of big data and means of analyzing big data.