Combinatorial Optimization and Machine Learning for Dynamic Inventory Routing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909096366571520 |
|---|---|
| author | Greif, Toni Bouvier, Louis Flath, Christoph M. Parmentier, Axel Rohmer, Sonja U. K. Vidal, Thibaut |
| author_facet | Greif, Toni Bouvier, Louis Flath, Christoph M. Parmentier, Axel Rohmer, Sonja U. K. Vidal, Thibaut |
| contents | We introduce a combinatorial optimization-enriched machine learning pipeline and a novel learning paradigm to solve inventory routing problems with stochastic demand and dynamic inventory updates. After each inventory update, our approach reduces replenishment and routing decisions to an optimal solution of a capacitated prize-collecting traveling salesman problem for which well-established algorithms exist. Discovering good prize parametrizations is non-trivial; therefore, we have developed a machine learning approach. We evaluate the performance of our pipeline in settings with steady-state and more complex demand patterns. Compared to previous works, the policy generated by our algorithm leads to significant cost savings, achieves lower inference time, and can even leverage contextual information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04463 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Combinatorial Optimization and Machine Learning for Dynamic Inventory Routing Greif, Toni Bouvier, Louis Flath, Christoph M. Parmentier, Axel Rohmer, Sonja U. K. Vidal, Thibaut Optimization and Control We introduce a combinatorial optimization-enriched machine learning pipeline and a novel learning paradigm to solve inventory routing problems with stochastic demand and dynamic inventory updates. After each inventory update, our approach reduces replenishment and routing decisions to an optimal solution of a capacitated prize-collecting traveling salesman problem for which well-established algorithms exist. Discovering good prize parametrizations is non-trivial; therefore, we have developed a machine learning approach. We evaluate the performance of our pipeline in settings with steady-state and more complex demand patterns. Compared to previous works, the policy generated by our algorithm leads to significant cost savings, achieves lower inference time, and can even leverage contextual information. |
| title | Combinatorial Optimization and Machine Learning for Dynamic Inventory Routing |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2402.04463 |