Authors: Yu (Billie) Zhang*, Department of Civil Engineering, University of Toronto, Dachuan Zhang, Department of Geography, Sun Yat-sen University, Eric J Miller, Department of Civil Engineering, University of Toronto
Topics: Urban Geography, Urban and Regional Planning, Spatial Analysis & Modeling
Keywords: Housing price modeling, Geographical Weighted Regression (GWR), Random Forrest (RF) model
Session Type: Paper
Presentation File: No File Uploaded
Previous housing price studies based on hedonic price modeling have mainly focused on applying various factors including built environment variables in the analysis, without establishing a comprehensive theoretical framework as a basis for the model formulation. To address this gap, this study introduces a more systematic framework for decomposing housing prices into land prices as determined by built form, , neighborhood socio-economic characteristics and individual dwellings’ physical conditions. Following this logic, this study experiments with the related variables through regression analysis, including consideration of spatial lags, as well as develops a housing price model using a random forest (RF) algorithm. A comprehensive time-series database of housing transaction data for the City of Toronto is used. Modeling results show that neighborhood social-economic factors contributed the most to the explanation of housing prices, while housing characteristics and accessibility measures were also significantly influential. Density and diversity in the built form dimension have less effect on prices. The RF model achieves an overall accuracy of 77%, a relatively good performance in reproducing observed prices. The framework and the model could provide the basis for further development of housing market models. The findings also provide insights for planners concerning factors influencing housing prices and, hence, residential location decision-making.