Exploring spatiotemporal patterns and influencing factors of ridesourcing and traditional taxi usage using geographically and temporally weighted regression method

ABSTRACT

The rivalry between ridesourcing and the traditional taxi has posed great challenges to traffic management authorities. Understanding the spatial patterns and influencing factors of their usage can help traffic authorities develop insightful policies and strategies to coordinate the operations of the two services better. This study develops a novel geographically and temporally weighted regression model (GTWR) to unravel the spatiotemporal patterns and influencing factors of the two services based on a high-resolution GPS dataset. The developed GTWR model achieves greater performance than other traditional methods. The results reveal that the spatiotemporal impacts of influencing factors on the usage of ridesourcing are quite different from that of traditional taxi. The spatiotemporal distribution and evolution of the coefficients are further discussed. The findings of the study could help traffic management authorities develop efficient regulatory policies to enhance the operations of the two services in specific areas and periods.

KEYWORDS:

• Ridesourcing
• traditional taxi
• spatiotemporal analysis
• GTWR

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by National Natural Science Foundation of China: [Grant Number 52002179]; Foundation for Jiangsu key Laboratory of Traffic and Transportation Security: [Grant Number TTS2020-03]; Nanjing Municipal Science and Technology Innovation Project for Overseas Scholars: [Grant Number 1007-YQR21045]; Fundamental Research Funds for the Central Universities: [Grant Number NS2021051].