Combinatorial Optimization-Enriched Machine Learning to Solve the Dynamic Vehicle Routing Problem with Time Windows
Problem
Logistics providers struggle to plan same-day deliveries: stochastic optimization is too slow online and reinforcement learning struggles with high-dimensional combinatorial problems.
Why it matters
Same-day delivery planning directly affects logistics service providers' daily operations, per the abstract.
What the AI did
A novel machine learning pipeline incorporating a combinatorial optimization layer solves a dynamic vehicle routing problem with dispatching waves.
Results
Ranked first in the EURO Meets NeurIPS 2022 Vehicle Routing Competition, outperforming all other approaches.
Impact
The first-place competition result externally benchmarks the method on the proposed routing problem.
Record
| Venue | Transportation Science |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Léo Baty, Kai Jungel, Patrick S. Klein, Axel Parmentier, Maximilian Schiffer |
| Citations | 69 (OpenAlex, at import time) |
| References | 28 |
| Model or method | ML pipeline with combinatorial optimization layer (no specific model named) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1287/trsc.2023.0107 |
| Open access | green |
| Keywords | vehicle routing, combinatorial optimization, machine learning, same-day delivery, NeurIPS competition |
Importance rating
significant — thousands to millions affected
Abstract states rising e-commerce and customer requirements create new daily planning complexity for logistics providers; same-day delivery routing is an industry-wide operational problem, scale unquantified.
More in Business & Industry
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Optimizing fraud detection in financial transactions with machine learning and imbalance mitigation | 2024 | 66 |
7
|
| 2 | BloombergGPT: A Large Language Model for Finance | 2023 | 289 |
6
|
| 3 | Search Personalization Using Machine Learning | 2020 | 167 |
6
|
| 4 | A review of the applications of multi-agent reinforcement learning in smart factories | 2022 | 76 |
6
|
| 5 | Credit risk prediction based on causal machine learning: Bayesian network learning, default inference, and interpretation | 2024 | 30 |
6
|