A Large-scale Last-mile Consolidation Model for E-commerce Home Delivery

E-commerce's rapid growth, combined with customer demand for fast shipping, has significantly escalated last-mile transportation, particularly home deliveries. This surge calls for novel strategies to optimize vehicle utilization while maintaining timely delivery. In response, many online retailers are incentivizing customers to embrace delayed home deliveries by offering economic incentives. Nonetheless, current transportation systems fall short in accommodating orders with extended delivery windows, primarily adhering to the First-In-First-Out rule and distance minimization via the Vehicle Routing Problem (VRP). In this paper, we introduce a new consolidation-based delivery methodology that addresses these challenges. Our approach accounts for orders with daily-based time windows and also anticipates future demand realizations (i.e., expected incoming orders). We characterize this consolidation problem using a Mixed Integer Linear Programming model and propose a custom metaheuristic approach that can tackle the problem on a large-scale setting, introducing a significant novelty approach in last-mile delivery research. We applied our methodology to one of Mexico's largest retailers and compared its performance against the company's existing transportation systems. O approach substantially improves vehicle utilization and yields considerable reductions in distance traveled, time, and overall transportation costs, achieving cost savings of up to 52%. These savings represent tangible benefits, enabling potential revenue enhancements for businesses and cost-effective, timely deliveries for consumers. Additionally, the increased vehicle utilization implies fewer vehicles are needed for the same volume of deliveries, thereby enhancing operational efficiency. This innovative approach, therefore, presents a practical and highly effective solution for managing large-scale last-mile delivery scenarios.