Smart Parcel Consolidation at Cainiao

Cainiao proposes a novel business model that consolidates parcels ordered by the same consumer from one or more merchants during the fulfillment process. The objective is to increase delivery speed without incurring additional costs for merchants and consumers. To support this business model, we develop three analytics methods: (1) a two-phase online optimization algorithm to determine which of a consumer’s parcels constitute consolidated parcels and to select the shipping methods for the consolidated parcels that maximize the gains while satisfying the constraints (e.g., the 10-day on-time delivery rate of all consumer parcels created within a specified time should reach a target value), (2) a statistical method to calculate delivery time distributions to obtain on-time delivery rates within different days, and (3) a simulation-based optimization method to guide managers in setting appropriate target values for the constraints. In addition, we prove that the expected optimality gap and constraint violation of the online optimization algorithm have sublinear bounds, and we validate its effectiveness and robustness by testing instances generated from real-world data. Since 2020, Cainiao has utilized the system to consolidate numerous parcels shipped from China to more than 50 countries and regions, thus saving tens of millions of dollars annually and reducing delivery time by at least 50%.

History: This paper has been accepted for the INFORMS Journal on Applied Analytics Special Issue—2023 Daniel H. Wagner Prize for Excellence in the Practice of Advanced Analytics and Operations Research.