Abstract

Last-mile logistics in Saudi megacities such as Riyadh, Jeddah, and Dammam face unprecedented challenges driven by rapid urbanization, escalating e-commerce demand, extreme climatic conditions, and complex traffic dynamics. Traditional delivery systems struggle with inefficient routing, unpredictable demand fluctuations, inadequate capacity planning, and suboptimal service levels, resulting in elevated operational costs, delayed deliveries, and environmental concerns. This article examines the application of data-driven decision models to optimize last-mile logistics operations in Saudi urban contexts. Leveraging advanced routing algorithms, machine learning-based demand forecasting, dynamic capacity planning frameworks, and service-level optimization techniques, these models enable logistics providers to achieve significant improvements in cost efficiency, delivery time reliability, and customer satisfaction while reducing carbon emissions and traffic congestion. The integration of real-time traffic data, historical delivery patterns, customer preference profiles, and geospatial information facilitates adaptive decision-making that responds to urban mobility constraints and seasonal demand variations. Implementation considerations specific to Saudi megacities include infrastructure readiness, data quality assurance, regulatory compliance, and workforce capability development. Future directions emphasize integration with emerging smart city platforms, autonomous delivery technologies, and real-time adaptive logistics systems that leverage Internet of Things sensors, connected vehicle networks, and artificial intelligence-driven coordination mechanisms to create resilient and sustainable urban delivery ecosystems.