An Interpretable Machine Learning-Based Analysis of Vehicle Yielding During Pedestrian-Vehicle Interactions at Unsignalized Intersections

The paper introduces an interpretable machine learning technique SHAP (SHapley Additive exPlanation) to analyze the vehicle yielding behaviors during pedestrian-vehicle interactions at unsignalized intersections. The study first extracts trajectory data from drone videos and then exploits machine learning methods to construct the yielding classification model. The results indicate that Random Forest (RF) outperforms Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and eXtreme Gradient Boosting (XGBoost), achieving the best classification performance with an area under the ROC curve (AUC) of 0.934. Finally, the SHAP algorithm is fused with RF to improve the model interpretability. The analysis reveals that the distances between vehicles and pedestrians make the most significant impact on vehicle yielding behavior. Furthermore, it is found that traffic-related variables exhibit non-linear and threshold effects on vehicle yielding.