Carpool-style ridesharing, compared to traditional solo ride-hailing, can reduce traffic congestion, cut per-passenger carbon emissions, reduce parking infrastructure, and provide a more cost-effective way to travel. Despite these benefits, ridesharing only occupies a small percentage of the total ride-hailing trips in cities. This study integrates big trip data with machine learning and eXplainable AI (XAI) to understand the factors that influence willingness to take shared rides. We use the City of Chicago as a case study, and results show that users tend to adopt ridesharing for longer distance trips, and the cost of a trip remains the most important factor. We identify a strong diurnal pattern that people prefer to request shared trips during the morning and afternoon peak hours. We also find socio-economic disparities: users who requested trips from neighbourhoods with a high percentage of non-white, a low median household income, a low percentage of bachelor’s degrees, and high vehicle ownership are more likely to share a ride. The findings and the XAI-based analytical framework presented in this study can help transportation network companies and local governments understand ridesharing behaviour and suggest new strategies and policies to promote the proportion of ridesharing for more sustainable and efficient city transportation.

与传统的单人打车相比，拼车式拼车可以减少交通拥堵，减少每位乘客的碳排放量，减少停车基础设施，并提供更具成本效益的出行方式。尽管有这些好处，但拼车只占城市总乘车行程的一小部分。本研究将大行程数据与机器学习和可解释的人工智能 (XAI) 相结合，以了解影响共享乘车意愿的因素。我们以芝加哥市为例，结果表明，用户倾向于采用拼车进行长途旅行，出行成本仍然是最重要的因素。我们发现了一种强烈的昼夜模式，人们更喜欢在早上和下午的高峰时段请求拼车。我们还发现社会经济差异：要求从非白人比例高、家庭收入中位数低、学士学位比例低和车辆拥有率高的社区出行的用户更有可能拼车。本研究中提出的调查结果和基于 XAI 的分析框架可以帮助交通网络公司和地方政府了解拼车行为，并提出新的战略和政策来提高拼车比例，以实现更可持续和高效的城市交通。