Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multi-Agent Learning of Efficient Fulfilment and Routing Strategies in E-Commerce (2311.16171v1)

Published 20 Nov 2023 in cs.AI, cs.LG, and cs.MA

Abstract: This paper presents an integrated algorithmic framework for minimising product delivery costs in e-commerce (known as the cost-to-serve or C2S). One of the major challenges in e-commerce is the large volume of spatio-temporally diverse orders from multiple customers, each of which has to be fulfilled from one of several warehouses using a fleet of vehicles. This results in two levels of decision-making: (i) selection of a fulfiLLMent node for each order (including the option of deferral to a future time), and then (ii) routing of vehicles (each of which can carry multiple orders originating from the same warehouse). We propose an approach that combines graph neural networks and reinforcement learning to train the node selection and vehicle routing agents. We include real-world constraints such as warehouse inventory capacity, vehicle characteristics such as travel times, service times, carrying capacity, and customer constraints including time windows for delivery. The complexity of this problem arises from the fact that outcomes (rewards) are driven both by the fulfiLLMent node mapping as well as the routing algorithms, and are spatio-temporally distributed. Our experiments show that this algorithmic pipeline outperforms pure heuristic policies.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (26)
  1. Barrie M. Baker and M.A. Ayechew. 2003. A genetic algorithm for the vehicle routing problem. Computers & Operations Research 30, 5 (2003), 787–800. https://doi.org/10.1016/S0305-0548(02)00051-5
  2. John E. Bell and Patrick R. McMullen. 2004. Ant colony optimization techniques for the vehicle routing problem. Advanced Engineering Informatics 18, 1 (2004), 41–48. https://doi.org/10.1016/j.aei.2004.07.001
  3. Alan Braithwaite and Edouard Samakh. 1998. The Cost-to-Serve Method. International Journal of Logistics Management, The 9 (01 1998), 69–84. https://doi.org/10.1108/09574099810805753
  4. Robin Cooper and Robert Kaplan. 1997. Cost & effect: using integrated cost systems to drive profitability and performance. (01 1997).
  5. Matthias Fey and Jan E. Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds.
  6. Utilizing graph machine learning within drug discovery and development. Briefings in bioinformatics 22, 6 (2021), bbab159.
  7. Deep Reinforcement Learning Algorithm for Fast Solutions to Vehicle Routing Problem with Time-Windows. In Joint International Conference on Data Science & Management of Data. 236–240.
  8. Charles W Haley and Robert C Higgins. 1973. Inventory policy and trade credit financing. Management science 20, 4-part-i (1973), 464–471.
  9. A linear decision rule for production and employment scheduling. Management Science 2, 1 (1955), 1–30.
  10. Brian Kallehauge. 2008a. Formulations and exact algorithms for the vehicle routing problem with time windows. Computers & Operations Research 35 (07 2008), 2307–2330. https://doi.org/10.1016/j.cor.2006.11.006
  11. Brian Kallehauge. 2008b. Formulations and Exact Algorithms for the Vehicle Routing Problem with Time Windows. Comput. Oper. Res. 35, 7 (jul 2008), 2307–2330. https://doi.org/10.1016/j.cor.2006.11.006
  12. Robert Kaplan and V.G. Narayanan. 2001. Measuring and managing customer profitability. 15 (09 2001).
  13. Harshad Khadilkar. 2022. Solving the capacitated vehicle routing problem with timing windows using rollouts and MAX-SAT. In Indian Control Conference.
  14. Learning combinatorial optimization algorithms over graphs. Advances in neural information processing systems 30 (2017).
  15. Douglas M Lambert and Martha C Cooper. 2000. Issues in supply chain management. Industrial marketing management 29, 1 (2000), 65–83.
  16. A graph neural networks-based deep Q-learning approach for job shop scheduling problems in traffic management. Information Sciences 607 (2022), 1211–1223. https://doi.org/10.1016/j.ins.2022.06.017
  17. Chryssi Malandraki and Mark Daskin. 1992a. Time Dependent Vehicle Routing Problems: Formulations, Properties and Heuristic Algorithms. Transportation Science 26 (08 1992), 185–200. https://doi.org/10.1287/trsc.26.3.185
  18. Chryssi Malandraki and Mark Daskin. 1992b. Time Dependent Vehicle Routing Problems: Formulations, Properties and Heuristic Algorithms. Transportation Science 26 (08 1992), 185–200. https://doi.org/10.1287/trsc.26.3.185
  19. Human-level control through deep reinforcement learning. nature 518, 7540 (2015), 529–533.
  20. Reinforcement learning for solving the vehicle routing problem. Advances in neural information processing systems 31 (2018).
  21. Learning to Minimize Cost to Serve for Multi-Node Multi-Product Order Fulfilment in Electronic Commerce. In International Conference on Data Science & Management of Data.
  22. Fast Approximate Solutions using Reinforcement Learning for Dynamic Capacitated Vehicle Routing with Time Windows. arXiv preprint arXiv:2102.12088 (2021).
  23. Spatio-temporal analysis and prediction of cellular traffic in metropolis. IEEE Transactions on Mobile Computing 18, 9 (2018), 2190–2202.
  24. Richard Wilding. 2020. Understanding Supply Chain cost drivers. In https://www.richardwilding.info/supply-chain-finance-and-cost-to-serve.html.
  25. Graph neural networks in recommender systems: a survey. Comput. Surveys 55, 5 (2022), 1–37.
  26. Graph Auto-Encoders for Network Completion. arXiv preprint arXiv:2204.11852 (2022).

Summary

We haven't generated a summary for this paper yet.