Learning to Bundle Proactively for On-Demand Meal Delivery

Abstract

On-demand meal delivery (ODMD) platforms such as DoorDash and Ele.me have experienced explosive growth in recent years. Effective logistics optimization strategies that could guarantee high service standards with controlled costs are crucial for the long-term sustainability of these platforms, and yet are also non-trivial due to the nature of ODMD operations. In particular, most of the orders are not known until they are placed by the customers, and any dispatching policy that only considers known requests would risk making myopic decisions in such a setting. In this paper, we propose a novel approach to address this problem. At the core of our method is a learning-based metric called Proactive Bundle Cost Vector (PBCV), which quantifies the easiness of bundling a particular order with future orders. Based on PBCV, we build a proactive bundling policy that that considers the viability of serving unknown requests. Extensive online A/B tests demonstrate that the resultant policy has shown significant improvements of key performance metrics over baseline policies. Our solution has been successfully deployed at one of the world's largest ODMD platforms, serving tens of millions of customers on a daily basis.