MSCT: Addressing Time-Varying Confounding with Marginal Structural Causal Transformer for Counterfactual Post-Crash Traffic Prediction

TL;DR

MSCT addresses time-varying confounding in post-crash traffic prediction by combining Marginal Structural Models with a causal transformer to estimate counterfactual speeds under hypothetical crash interventions. It employs a dual-path sequence-to-sequence architecture with propensity-score and domain-generalization losses to learn invariant causal features while predicting heterogeneous treatment responses. A synthetic data generation procedure mirrors the causal mechanism between traffic speed, crashes, and covariates, enabling evaluation in the absence of ground-truth counterfactuals, and MSCT outperforms state-of-the-art baselines on both synthetic and real-world data, especially for longer horizons. The work provides insights into bias management and dataset distribution effects for counterfactual prediction in intelligent transportation systems, with future directions including spatial causal modeling and broader transport contexts.

Abstract

Traffic crashes profoundly impede traffic efficiency and pose economic challenges. Accurate prediction of post-crash traffic status provides essential information for evaluating traffic perturbations and developing effective solutions. Previous studies have established a series of deep learning models to predict post-crash traffic conditions, however, these correlation-based methods cannot accommodate the biases caused by time-varying confounders and the heterogeneous effects of crashes. The post-crash traffic prediction model needs to estimate the counterfactual traffic speed response to hypothetical crashes under various conditions, which demonstrates the necessity of understanding the causal relationship between traffic factors. Therefore, this paper presents the Marginal Structural Causal Transformer (MSCT), a novel deep learning model designed for counterfactual post-crash traffic prediction. To address the issue of time-varying confounding bias, MSCT incorporates a structure inspired by Marginal Structural Models and introduces a balanced loss function to facilitate learning of invariant causal features. The proposed model is treatment-aware, with a specific focus on comprehending and predicting traffic speed under hypothetical crash intervention strategies. In the absence of ground-truth data, a synthetic data generation procedure is proposed to emulate the causal mechanism between traffic speed, crashes, and covariates. The model is validated using both synthetic and real-world data, demonstrating that MSCT outperforms state-of-the-art models in multi-step-ahead prediction performance. This study also systematically analyzes the impact of time-varying confounding bias and dataset distribution on model performance, contributing valuable insights into counterfactual prediction for intelligent transportation systems.

Figures (9)

• Figure 1: Illustration of counterfactual traffic speed under the impact of crashes.
• Figure 2: Causal graph for factors interacting mechanism over time.
• Figure 3: The architecture of MSCT.
• Figure 4: The architecture of transformer blocks.
• Figure 5: Synthetic traffic speed data samples. Red dashed line denotes the time of crash occurrence.