A prescriptive analytics framework for efficient E-commerce order delivery

Achieving timely last-mile order delivery is often the most challenging part of an e-commerce fulfillment. Effective management operations can result in significant cost savings and lead to increased customer satisfaction. Currently, due lack availability information, schedules followed by agents are optimized for shortest tour distance. Therefore, orders not delivered customer-preferred time periods resulting missed deliveries. Missed deliveries undesirable since they incur additional costs. In this paper, we propose a decision support framework that intended improve success rates while reducing Our generates predicting appropriate delivery. particular, proposed works two stages. first stage, every throughout shift predicted using machine learning models. The predictions used as input optimization scheme, which second stage. evaluated on real-world datasets collected from large platform. results indicate effectiveness enabling up 10.2% costs when compared current industry practice.