Counterfactual Explanations for Deep Learning-Based Traffic Forecasting

arXiv:2405.00456v1 Announce Type: new
Abstract: Deep learning models are widely used in traffic forecasting and have achieved state-of-the-art prediction accuracy. However, the black-box nature of those models makes the results difficult to interpret by users. This study aims to leverage an Explainable AI approach, counterfactual explanations, to enhance the explainability and usability of deep learning-based traffic forecasting models. Specifically, the goal is to elucidate relationships between various input contextual features and their corresponding predictions. We present a comprehensive framework that …

abstract accuracy art arxiv box counterfactual cs.ai cs.lg deep learning explainability explainable ai forecasting however nature prediction results state study traffic type usability