<![CDATA[Urban transportation networks are characterized by complex spatial structures, dynamic traffic conditions, uncertain travel times, and heterogeneous road characteristics. Conventional shortest-path algorithms, such as Dijkstra's algorithm, generally optimize a predetermined edge cost and therefore may not adequately represent rapidly changing traffic conditions. This study proposes an explainable machine learning framework for shortest-path optimization in urban transportation networks by integrating traffic-time prediction, graph-based representation, shortest-path optimization, and explainable artificial intelligence. The transportation network is represented as a directed weighted graph (G=(V,E)), where vertices represent intersections and edges represent road segments. A machine learning model estimates the expected travel time of each road segment using traffic-related features, including historical speed, traffic volume, road length, congestion level, time of day, day of week, and weather-related variables. The predicted travel time is then incorporated into a dynamic edge-weight function and optimized using a shortest-path algorithm. To improve transparency, SHAP-based explanations are employed to quantify the contribution of each input feature to predicted travel time and, consequently, to route selection. The proposed framework is evaluated using conventional distance-based routing, static travel-time routing, machine-learning-based routing, and explainable machine-learning-based routing. Illustrative simulation results indicate that incorporating predicted traffic conditions can reduce estimated travel time compared with static shortest-path routing, while the XAI component provides a transparent interpretation of why particular road segments are selected or avoided. The proposed approach provides a mathematical and interpretable framework for intelligent urban route planning and can support transportation agencies in developing more adaptive, transparent, and trustworthy intelligent transportation systems. ]]>
