Project Scheduling, Resource Allocation, and AI-Based Optimization as Drivers of Last-Mile Logistics Efficiency in Nigeria (Published)
This study examines how resource allocation, project scheduling, and AI-based optimization interact to improve last-mile logistics performance in Nigeria’s changing supply chain environment. The final mile phase, which makes up the most expensive and operationally challenging part of logistics, is still limited by a lack of infrastructure, manual scheduling, and disjointed data systems. Utilizing survey data from 200 logistics experts in key Nigerian cities, the study employs a quantitative explanatory methodology, drawing on project scheduling theory and combinatorial optimization models. To investigate the proposed correlations and the mediating role of AI optimization, descriptive, regression, and structural equation modeling (SEM) analyses were performed. The findings showed that last-mile performance is significantly predicted by project scheduling (β = 0.455, p < 0.001), resource allocation (β = 0.298, p = 0.002), and AI optimization (β = 0.426, p < 0.001), which together account for 23.9% of the variance in last-mile performance (R2 = 0.239). Excellent fit was demonstrated by the SEM model (CFI = 0.954; RMSEA = 0.046), indicating that scheduling and resource management have an impact on delivery efficiency that is mediated by AI optimization. The results highlight how, in order to attain operational accuracy and environmental balance, Nigeria’s logistics industry must integrate data-driven scheduling, intelligent resource deployment, and sustainability-oriented AI technologies.
Keywords: AI optimization, Resource Allocation, last-mile logistics, project scheduling, structural equation modeling