A Decision-Centered Assessment of Explainable AI in Transport Logistics
Ismail Abdulrashid, Md Talha Mohsin, Mohamed Khalafalla, Dursun Delen · Journal of Computer Information Systems · 2026
Artificial intelligence (AI) is increasingly used to support decision-making in transport logistics, yet prior research has focused mainly on predictive accuracy and computational performance, with limited attention to how AI systems operate within real decision processes. In particular, the role of explainable artificial intelligence (XAI) in supporting human judgment, accountability, and organizational decision-making remains fragmented. This study presents a structured narrative review of 51 peer-reviewed journal articles published between 2015 and 2026, retrieved from Scopus, and examines AI-enabled decision support in transport logistics from a decision-centered perspective. Rather than organizing studies only by modeling techniques, the review synthesizes the literature across decision level, authority allocation, temporal structure, functional AI roles, and explanation design. The findings show a strong emphasis on operational, high-frequency predictive decision support, with explainability primarily implemented as post hoc feature attribution. The review identifies key gaps and proposes directions to better align explainable AI with real-world transport logistics decision-making.