Travel Behaviour and Society最新文献

英文中文

Who waits longer to pick you up? behavioral and spatial inequities in ride-hailing pickup time based on real-world platform data 谁等得更久才来接你？基于真实平台数据的网约车接送时间的行为和空间不平等

IF 5.7 2区工程技术 Q1 TRANSPORTATION

Travel Behaviour and Society

Pub Date : 2026-04-01 Epub Date: 2025-12-29 DOI: 10.1016/j.tbs.2025.101224

Jiayan Zhang , Jiao Jiao , Xiang Wang , Inhi Kim , Tianqi Gu

Pickup time at the post-matching stage is a critical but often overlooked dimension of service equity in ride-hailing systems. While existing studies often rely on modeled or inferred estimates of wait time based on distance, traffic conditions, or simulation outcomes, few have access to actual pickup time records linked to real-name ride-hailing transactions. This study draws on a rare, real-world dataset comprising platform-recorded pickup durations and real-name verified driver profiles from Suzhou, China. Using a Geographically Weighted Random Forest (GWRF) model with SHAP interpretation, we examine how pickup responsiveness varies across driver characteristics (gender, age, residency), geography (central vs. peripheral zones), and time (weekday vs. holiday). Our findings show that young, local male drivers tend to achieve faster pickups due to broader geographic coverage and incentive sensitivity, while older, non-local female drivers face slower pickups, especially under uncertain or high-risk conditions. Moreover, spatial and temporal patterns reveal that conventional assumptions—such as the edge disadvantage or vehicle density effects—do not hold uniformly across groups. These findings suggest that pickup time is a socially embedded outcome rather than a purely algorithmic one. Building on this perspective, we propose behavior-aware dispatch strategies, targeted driver support programs, and regulatory design implications aimed at enhancing equity, inclusion, and responsiveness in ride-hailing governance.

在网约车系统中，匹配后阶段的接车时间是服务公平的一个关键因素，但往往被忽视。虽然现有的研究通常依赖于基于距离、交通状况或模拟结果的模型或推断的等待时间估计，但很少有人能够获得与实名叫车交易相关的实际取车时间记录。本研究利用了一个罕见的、真实的数据集，其中包括来自中国苏州的平台记录的取车时间和实名验证的司机资料。使用具有SHAP解释的地理加权随机森林（GWRF）模型，我们研究了不同驾驶员特征（性别、年龄、居住地）、地理位置（中心与外围区域）和时间（工作日与假日）的取车响应性差异。我们的研究结果表明，由于地理覆盖范围更广和激励敏感性，年轻的本地男性司机往往能够更快地接车，而年长的非本地女性司机则面临更慢的接车速度，尤其是在不确定或高风险的情况下。此外，空间和时间模式表明，传统的假设——如边缘劣势或车辆密度效应——在不同的群体中并不一致。这些发现表明，接送时间是一个社会嵌入的结果，而不是纯粹的算法。基于这一观点，我们提出了行为感知调度策略、有针对性的司机支持计划和监管设计启示，旨在提高网约车治理中的公平性、包容性和响应性。

{"title":"Who waits longer to pick you up? behavioral and spatial inequities in ride-hailing pickup time based on real-world platform data","authors":"Jiayan Zhang , Jiao Jiao , Xiang Wang , Inhi Kim , Tianqi Gu","doi":"10.1016/j.tbs.2025.101224","DOIUrl":"10.1016/j.tbs.2025.101224","url":null,"abstract":"<div><div>Pickup time at the post-matching stage is a critical but often overlooked dimension of service equity in ride-hailing systems. While existing studies often rely on modeled or inferred estimates of wait time based on distance, traffic conditions, or simulation outcomes, few have access to actual pickup time records linked to real-name ride-hailing transactions. This study draws on a rare, real-world dataset comprising platform-recorded pickup durations and real-name verified driver profiles from Suzhou, China. Using a Geographically Weighted Random Forest (GWRF) model with SHAP interpretation, we examine how pickup responsiveness varies across driver characteristics (gender, age, residency), geography (central vs. peripheral zones), and time (weekday vs. holiday). Our findings show that young, local male drivers tend to achieve faster pickups due to broader geographic coverage and incentive sensitivity, while older, non-local female drivers face slower pickups, especially under uncertain or high-risk conditions. Moreover, spatial and temporal patterns reveal that conventional assumptions—such as the edge disadvantage or vehicle density effects—do not hold uniformly across groups. These findings suggest that pickup time is a socially embedded outcome rather than a purely algorithmic one. Building on this perspective, we propose behavior-aware dispatch strategies, targeted driver support programs, and regulatory design implications aimed at enhancing equity, inclusion, and responsiveness in ride-hailing governance.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"43 ","pages":"Article 101224"},"PeriodicalIF":5.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}