Ridesharing is critical for promoting transportation sustainability. As a new form of ridesharing services, ridesplitting has rarely been studied. Based on the Chicago ridesourcing trip data, this study explores how ridesplitting adoption rate (i.e., the proportion of ridesourcing trips with ridesharing authorization) varies across space and what factors are associated with these variations. We find large variations in ridesplitting adoption rates across neighborhoods (Census Tracts) and across origin–destination (Census-Tract-to-Census-Tract) pairs. Particularly, the ridesplitting adoption rate is low for airport rides. We further apply a random forest model to explore which factors are key predictors of ridesplitting adoption rate across O-D pairs and to explore their nonlinear associations. The results suggest that the socioeconomic and demographic variables collectively contribute to 68.60% of the predictive power of the model, but travel-cost variables and built-environment-related factors are also important. The most important variables associated with ridesplitting adoption are ethnic composition, median household income, education level, trip distance, and neighborhood density. We further examine the nonlinear association between neighborhood ridesplitting adoption rate and several key variables such as the percentage of white population, median household income, and neighborhood Walk Score. The revealed nonlinear patterns can help transportation professionals identify neighborhoods with the greatest potential to promote ridesplitting.

拼车对于促进交通运输的可持续性至关重要。作为一种新的拼车服务形式，很少研究拼车。基于芝加哥乘车旅行的数据，本研究探讨了乘车拆分采用率（即获得乘车共享授权的乘车旅行的比例）如何在空间上变化以及与这些变化相关的因素。我们发现跨社区（人口普查区域）和起源-目的地（人口普查区域到人口普查区域）对的搭便车采用率存在很大差异。特别地，对于机场乘车而言，乘车采用率较低。我们进一步应用随机森林模型来研究哪些因素是跨OD对搭便车采用率的关键预测因素，并探讨它们的非线性关联。结果表明，社会经济和人口变量共同贡献了该模型的68.60％的预测能力，但是旅行成本变量和与建筑环境有关的因素也很重要。与搭便车有关的最重要变量是种族构成，家庭收入中位数，教育水平，出行距离和社区密度。我们进一步研究了邻里拼车采用率与几个关键变量之间的非线性关联，例如白人人口百分比，家庭收入中位数和邻里步行得分。揭示的非线性模式可以帮助运输专业人士确定最有可能促进拼车的邻里。但是旅行成本变量和与建筑环境相关的因素也很重要。与搭便车有关的最重要变量是种族构成，家庭收入中位数，教育水平，出行距离和社区密度。我们进一步研究了邻里拼车采用率与几个关键变量之间的非线性关联，例如白人人口百分比，家庭收入中位数和邻里步行得分。揭示的非线性模式可以帮助运输专业人士确定最有可能促进拼车的邻里。但是旅行成本变量和与建筑环境相关的因素也很重要。与搭便车有关的最重要变量是种族构成，家庭收入中位数，教育水平，出行距离和社区密度。我们进一步研究了邻里拼车采用率与几个关键变量之间的非线性关联，例如白人人口百分比，家庭收入中位数和邻里步行得分。揭示的非线性模式可以帮助运输专业人士确定最有可能促进拼车的邻里。和邻里密度。我们进一步研究了邻里拼车采用率与几个关键变量之间的非线性关联，例如白人人口百分比，家庭收入中位数和邻里步行得分。揭示的非线性模式可以帮助运输专业人士确定最有可能促进拼车的社区。和邻里密度。我们进一步研究了邻里拼车采用率与几个关键变量之间的非线性关联，例如白人人口百分比，家庭收入中位数和邻里步行得分。揭示的非线性模式可以帮助运输专业人士确定最有可能促进拼车的邻里。