Exploration of Differences in Housing Price Determinants Based on Street View Imagery and the Geographical-XGBoost Model: Improving Quality of Life for Residents and Through-Travelers
Open Access
- 9 October 2025
- journal article
- research article
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 14 (10) , 391
Abstract
Street design quality and socio-economic factors jointly influence housing prices, but their intertwined effects and spatial variations remain under-quantified. Housing prices not only reflect residents’ neighborhood experiences but also stem from the spillover value of public streets perceived and used by different users. This study takes Tianjin as a case and views the street environment as an immediate experience proxy for through-travelers, combining street view images and crowdsourced perception data to extract both subjective and objective indicators of the street environment, and integrating neighborhood and location characteristics. We use Geographical-XGBoost to evaluate the relative contributions of multiple factors to housing prices and their spatial variations. The results show that incorporating both subjective and objective street information into the Hedonic Pricing Model (HPM) improves its explanatory power, while local modeling with G-XGBoost further reveals significant heterogeneity in the strength and direction of effects across different locations. The results indicate that incorporating both subjective and objective street information into the HPM enhances explanatory power, while local modeling with G-XGBoost reveals significant heterogeneity in the strength and direction of effects across different locations. Street greening, educational resources, and transportation accessibility are consistently associated with higher housing prices, but their strength varies by location. Core urban areas exhibit a “counterproductive effect” in terms of complexity and recognizability, while peripheral areas show a “barely acceptable effect,” which may increase cognitive load and uncertainty for through-travelers. In summary, street environments and socio-economic conditions jointly influence housing prices via a “corridor-side–community-side” dual-pathway: the former (enclosure, safety, recognizability) corresponds to immediate improvements for through-travelers, while the latter (education and public services) corresponds to long-term improvements for residents. Therefore, core urban areas should control design complexity and optimize human-scale safety cues, while peripheral areas should focus on enhancing public services and transportation, and meeting basic quality thresholds with green spaces and open areas. Urban renewal within a 15 min walking radius of residential areas is expected to collaboratively improve daily travel experiences and neighborhood quality for both residents and through-travelers, supporting differentiated housing policy development and enhancing overall quality of life.Keywords
Funding Information
- The Tianjin Art Science Planning General Project (A22039)
This publication has 80 references indexed in Scilit:
- Geographical-XGBoost: a new ensemble model for spatially local regression based on gradient-boosted treesJournal of Geographical Systems, 2025
- Transformer-based semantic segmentation for large-scale building footprint extraction from very-high resolution satellite imagesAdvances In Space Research, 2024
- Towards safer streets: A framework for unveiling pedestrians’ perceived road safety using street view imageryAccident Analysis & Prevention, 2023
- The effects of jobs, amenities, and locations on housing submarkets in Xiamen City, ChinaJournal of Housing and the Built Environment, 2022
- Scale and local modeling: new perspectives on the modifiable areal unit problem and Simpson’s paradoxJournal of Geographical Systems, 2022
- Migration and inequality in rental housing: Affordability stress in the Chinese citiesApplied Geography, 2020
- Measuring visual enclosure for street walkability: Using machine learning algorithms and Google Street View imageryApplied Geography, 2016
- Deep Learning the City: Quantifying Urban Perception at a Global Scale2016
- Sample size planning for classification modelsAnalytica Chimica Acta, 2013
- Using Google Street View to Audit Neighborhood EnvironmentsAmerican Journal of Preventive Medicine, 2011