Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2022
Abstract
In this research, a taxi travel time based Geographically Weighted Regression model (GWR) is proposed and utilized to model the public housing price in the case study of Singapore. In addition, a comparison between the proposed taxi data driven GWR and other models, such as ordinary least squares model (OLS), GWR model based on Euclidean distance and GWR model based on public transport travel time, have also been carried out. Results indicates that taxi travel time based GWR model has better fitting performance than the OLS model, and slightly better than the Euclidean distance-based GWR model, however, it is not as good as the GWR model based on public transport travel time according to the metric of Adjusted R2. These experiments indicate that the public transport travel time may has a major part to play in modeling the public housing resale prices compared to taxi travel time or driving time, and both the taxi travel time and public transport travel time can better explain the public housing resale prices in Singapore compared to Euclidean distance in the GWR modeling.
Keywords
Hedonic model, GWR, Public housing prices, Taxi travel time
Discipline
Computer Engineering
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of the 29th International Conference on Geoinformatics, Beijing, China, 2022 June 15 - 18
Identifier
10.1109/Geoinformatics57846.2022.9963833
Publisher
IEEE
City or Country
Beijing, China
Citation
WANG, Yi’an; CAI, Fangyi; CHENG, Shih-Fen; WU, Bo; and CAO, Kai.
Taxi travel time based Geographically Weighted Regression Model (GWR) for modeling public housing prices in Singapore. (2022). Proceedings of the 29th International Conference on Geoinformatics, Beijing, China, 2022 June 15 - 18.
Available at: https://ink.library.smu.edu.sg/sis_research/7708
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/Geoinformatics57846.2022.9963833