Exploring spatiotemporal patterns and influencing factors of ridesourcing and traditional taxi usage using geographically and temporally weighted regression method
Exploring spatiotemporal patterns and influencing factors of ridesourcing and traditional taxi usage using geographically and temporally weighted regression method
复制标题
DOI：
10.1080/03081060.2023.2166510
复制
发表时间：
2023-01
影响因子：
1.6
通讯作者：
J. Bao;Zongbo Wang;Zhao Yang;Xiaoxuan Shan
中科院分区：
文献类型：
--
作者：
J. Bao;Zongbo Wang;Zhao Yang;Xiaoxuan Shan
摘要网约车与传统出租车的竞争给交通管理部门带来了巨大的挑战。了解其使用的空间模式和影响因素可以帮助交通管理部门制定有见地的政策和战略，以更好地协调这两种服务的运营。本文基于高分辨率GPS数据集，提出了一种新的时空加权回归模型（GTWR），以揭示这两种服务的时空模式及其影响因素。所开发的GTWR模型实现了比其他传统方法更好的性能。研究结果表明，网约车出行影响因素的时空效应与传统出租车出行有很大不同。进一步讨论了这些系数的时空分布和演化规律。研究结果可协助交通管理当局制订有效的规管政策，以加强两条巴士线在特定地区及时段的运作。
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.