Urban logistics networks have undergone rapid transformation due to increasing consumer demand, e-commerce expansion, and the growing complexity of last-mile delivery operations. Despite technological advancements, inefficiencies persist in the final leg of the delivery process, often leading to increased costs, environmental burdens, and diminished customer satisfaction. This paper proposes a Predictive Data Analytics Model (PDAM) to enhance last-mile delivery efficiency in urban logistics. By leveraging a literature-based methodology and analyzing over 100 peer-reviewed sources, the study synthesizes existing approaches in predictive analytics, logistics optimization, and urban freight systems. The model integrates real-time data, machine learning techniques, and geospatial intelligence to forecast delivery constraints, optimize routing, and improve service reliability. Structured into a detailed introduction, literature review, model design, discussion, and conclusion, this paper provides a strategic framework for logistics planners, policymakers, and technology implementers seeking to transform urban delivery ecosystems.
last-mile delivery, predictive analytics, urban logistics, routing optimization, machine learning, delivery efficiency
IRE Journals:
Opeyemi Morenike Filani , John Oluwaseun Olajide , Grace Omotunde Osho , Patience Okpeke Paul
"A Predictive Data Analytics Model for Enhancing Last-Mile Delivery Efficiency in Urban Logistics Networks" Iconic Research And Engineering Journals Volume 3 Issue 3 2019 Page 181-192
IEEE:
Opeyemi Morenike Filani , John Oluwaseun Olajide , Grace Omotunde Osho , Patience Okpeke Paul
"A Predictive Data Analytics Model for Enhancing Last-Mile Delivery Efficiency in Urban Logistics Networks" Iconic Research And Engineering Journals, 3(3)