Do street-level scene perceptions affect housing prices in Chinese megacities? An analysis using open access datasets...

Area of Science:

• Urban Planning
• Environmental Economics
• Real Estate Analysis

Background:

• The hedonic price model (HPM) is commonly used to study housing prices and environmental factors.
• Few studies have investigated the impact of scene perception near residential units on housing values.

Purpose of the Study:

• To propose and validate an open-access-dataset-based hedonic price modeling (OADB-HPM) framework.
• To quantify the impact of scene perception characteristics on housing prices in Beijing and Shanghai.
• To analyze the relationship between urban scene components and resident perception.

Main Methods:

• Utilized house purchasing records from FANG.com and open-access geolocation data (street view pictures, POI, road networks).
• Employed a deep learning framework with Baidu street view panoramas to quantify greenery, sky, and building view indexes (GVI, SVI, BVI).
• Integrated scene perception characteristics with traditional factors in the HPM to calculate marginal housing prices.

Main Results:

• Greenery and sky view indexes significantly increased housing prices in Beijing (RMB 39,377 and 6,011) and Shanghai (RMB 21,689 and 2,763).
• Buyers demonstrate a higher willingness to pay for properties with better natural environmental perceptions.
• Results were compared between Beijing and Shanghai.

Conclusions:

• The OADB-HPM framework effectively quantifies urban scene perception's impact on housing prices.
• Decision-makers and planners can use these quantification tools to understand resident-urban scene interactions.
• Enhancing natural elements in urban environments can positively influence housing market values.