Causal inference with the difference-in-differences (DID) framework is popular in identifying causal effects with observational data and has started to be applied in recent travel behaviour studies. Most relevant transportation research adopts the conventional linear parametric DID model, which is known to be inflexible and restrictive. This study applies non-parametric DID estimators facilitated by machine learning (ML) models for causal inference in a variety of data scenarios. Semi-parametric and doubly robust estimators are established and integrated with the ML-based cross-fitting pipeline. Simulation studies and empirical case studies are conducted to showcase the ability of ML-based DID to detect causal effects from both simulated and real-world datasets. Results suggest that the proposed methods outperform conventional DID models in all data scenarios. Light working models are generally preferred over hyperparameter-dependent ones for their comparable performance, lower computational burden, and higher levels of compatibility to real-world empirical analysis. Empirical case studies also demonstrate how the proposed DID method could be applied to evaluate the impacts of various interventions on travel behaviour in different contexts. The present study adds to the existing travel behaviour literature by leveraging machine learning algorithms and non-parametric estimators to the impact evaluation of external interventions on travel characteristics and expanding the application of causal inference approaches in transportation research.

中文翻译：

---

基于机器学习的因果推理，用于评估旅行行为研究的干预：双重差异框架


使用双重差异（DID）框架进行因果推断在通过观察数据识别因果效应方面很流行，并且已开始应用于最近的旅行行为研究中。大多数相关交通研究都采用传统的线性参数 DID 模型，该模型缺乏灵活性且具有限制性。本研究应用机器学习 (ML) 模型促进的非参数 DID 估计器在各种数据场景中进行因果推理。建立了半参数和双鲁棒估计器，并将其与基于 ML 的交叉拟合管道集成。进行模拟研究和实证案例研究是为了展示基于 ML 的 DID 从模拟和现实数据集中检测因果效应的能力。结果表明，所提出的方法在所有数据场景中都优于传统的 DID 模型。轻工作模型通常比依赖超参数的模型更受青睐，因为它们具有可比的性能、较低的计算负担以及与现实世界实证分析的更高水平的兼容性。实证案例研究还证明了如何应用所提出的 DID 方法来评估各种干预措施对不同背景下出行行为的影响。本研究通过利用机器学习算法和非参数估计器来评估外部干预对出行特征的影响，并扩展因果推理方法在交通研究中的应用，对现有的出行行为文献进行了补充。