Amazon Locker Capacity Management
Abstract: Amazon Locker is a self-service delivery or pickup location where customers can pick up packages and drop off returns. A basic first-come-first-served policy for accepting package delivery requests to lockers results in lockers becoming full with standard shipping speed (3-5 day shipping) packages, and leaving no space left for expedited packages which are mostly Next-Day or Two-Day shipping. This paper proposes a solution to the problem of determining how much locker capacity to reserve for different ship-option packages. Yield management is a much researched field with popular applications in the airline, car rental, and hotel industries. However, Amazon Locker poses a unique challenge in this field since the number of days a package will wait in a locker (package dwell time) is, in general, unknown. The proposed solution combines machine learning techniques to predict locker demand and package dwell time, and linear programming to maximize throughput in lockers. The decision variables from this optimization provide optimal capacity reservation values for different ship options. This resulted in a year-over-year increase of 9% in Locker throughput worldwide during holiday season of 2018, impacting millions of customers.
- Carnival optimizes revenue and inventory across heterogenous cruise line brands. INFORMS Journal on Applied Analytics, 51(1):26–41, 2021.
- G. Bitran and R. Caldentey. An overview of pricing models for revenue management. Manufacturing & Service Operations Management, 5:203–229, 2003.
- A. Bruce. Personal communication, 2019.
- New formulations for price and ticket availability decisions in choice-based network revenue management. In AGIFORS 55th Annual Symposium: Analytics for Efficiency and Customer Centric Optimization, Washington, D.C., August 2015. Airline Group of the International Federation of Operational Research Societies (AGIFORS).
- J.B. Feldman and H. Topaloglu. Revenue management under the Markov Chain choice model. Operations Research, 65:1322–1342, 2017.
- Online network revenue management using thompson sampling. Operations Research, 66:1586–1602, 2018.
- R. Gopalakrishnan and N. Rangaraj. Capacity management on long-distance passenger trains of Indian Railways. Interfaces, 40(4):291–302, 2010.
- M.F. Gorman. Hub Group implements a suite of OR tools to improve its operations. Interfaces, 40(5):368–384, 2010.
- Europcar integrates forecasting, simulation, and optimization techniques in a capacity and revenue management system. INFORMS Journal on Applied Analytics, 49(1):40–51, 2019.
- Analysis of Parcel Lockers’ Efficiency as the Last Mile Delivery Solution – The Results of the Research in Poland. In Tenth International Conference on City Logistics 17-19 June 2015, volume 12 of Transportation Research Procedia, pages 644–655, 2016.
- Incorporating network flow effects into the airline fleet assignment process. Transportation Science, 42(4):514–529, 2008.
- S. Kunnumkal and K. Talluri. A strong Lagrangian relaxation for general discrete-choice network revenue management. Computational Optimization and Applications, 73:275–310, 2019.
- K. Littlewood. Forecasting and control of passenger bookings. In Proceedings of 12th AGIFORS Symposium, pages 95–117, Nathanya, Israel, October 1972.
- K. Littlewood. Forecasting and control of passenger bookings. Journal of Revenue and Pricing Management, 4(2):111–123, 2005.
- J.I. McGill. Optimization and estimation problems in airline yield management. PhD thesis, University of British Columbia, December 1989.
- J.I. McGill and G.J. van Ryzin. Revenue management: Research overview and prospects. Transportation Science, 33:233–256, 1999.
- Flexible parcel delivery to automated parcel lockers: Models, solution methods and analysis. EURO Journal on Transportation and Logistics, 8:683–711, 2019.
- Survey on revenue management in media and broadcasting. Interfaces, 47(3):195–213, 2017.
- R.L. Phillips. Pricing and revenue optimization. Stanford University Press, 2005.
- S. Rohmer and B. Gendron. A guide to parcel lockers in last mile distribution – Highlighting challenges and opportunities from an OR perspective. Technical Report CIRRELT-2020-11, CIRRELT, Université de Montréal, 2020.
- Capacity management system for delivery lockers, U.S. Patent 11 526 838, Dec. 2022.
- Autonomous airline revenue management: A deep reinforcement learning approach to seat inventory control and overbooking. In Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 36th International Conference on Machine Learning, Long Beach, California, 2019.
- Yield management at American Airlines. Interfaces, 22(1):8–31, 1992.
- Revenue management: Models and methods. In Proceedings of the 2009 Winter Simulation Conference, pages 148–161, Austin, Texas, 2009.
- From home delivery to parcel lockers: A case study in amsterdam. Transportation Research Procedia, 46:37–44, 2020.
- K.W. Wang. Optimum seat allocation for multi-leg flights with multiple fare types. In Proceedings of the Twenty-third annual symposium - AGIFORS, Airline Group of the International Federation of Operational Research Societies, Olive Branch, Mississippi, 1983.
- Learning theory and algorithms for revenue management in sponsored search. Technical Report 1807.01827, arXiv, 2018.
- A comparison of forecasting methods for hotel revenue management. Technical report, Cornell University, School of Hotel Administration site, 2003. URL http://scholarship.sha.cornell.edu/articles/753. Retrieved from institution site on 2020-04-24.
- B. Zadrozny and C. Elkan. Transforming classifier scores into accurate multiclass probability estimates. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 694–699. ACM, 2002.
Paper Prompts
Sign up for free to create and run prompts on this paper.