Paper Info
Title
Alibaba Vehicle Routing Algorithms Enable Rapid Pick and Delivery
Abstract
Alibaba Group pioneered integrated online and offline retail models to allow customers to place online orders of e-commerce and grocery products at its participating stores or restaurants for rapid delivery-in some cases, in as little as 30 minutes after an order has been placed. To meet these service commitments, quick online routing decisions must be made to optimize order picking routes at warehouses and delivery routes for drivers. The solutions to these routing problems are complicated by stringent service commitments, uncertainties, and complex operations in warehouses with limited space. Alibaba has developed a set of algorithms for vehicle routing problems (VRPs), which include an open-architecture adaptive large neighborhood search to support the solution of variants of routing problems and a deep learning-based approach that trains neural network models offline to generate almost instantaneous solutions online. These algorithms have been implemented to solve VRPs in several Alibaba subsidiaries, have generated more than $50 million in annual financial savings, and are applicable to the broader logistics industry. The success of these algorithms has fermented an inner-source community of operations researchers within Alibaba, boosted the confidence of the company's executives in operations research, and made operations research one of the core competencies of Alibaba Group.
Year
DOI
Venue
2022
10.1287/inte.2021.1108
INFORMS JOURNAL ON APPLIED ANALYTICS
Keywords
DocType
Volume
vehicle routing problems, last-mile delivery, adaptive large neighborhood search, deep reinforcement learning, inner source, Edelman Award
Journal
52
Issue
ISSN
Citations 
1
2644-0865
0
PageRank 
References 
Authors
0.34
0
9
Name
Order
Citations
PageRank
Haoyuan Hu100.34
Ying Zhang200.34
Jiangwen Wei300.34
Yang Zhan400.34
Xinhui Zhang500.34
Shaojian Huang600.34
Guangrui Ma700.34
Yuming Deng862.44
Siwei Jiang900.34