In-Context Quantile Regression for Multi-Product Inventory Management Using Time-Series Transformers

Abstract

This paper proposes a novel universal quantile regression approach for solving a multi-product inventory management problem, leveraging the in-context learning (ICL) capability of time-series transformers. Our work not only provides a new meta-learning approach for multi-product inventory management, but also extends the state-of-the-art in ICL of transformers by showing how they can be used as universal quantile regressors for data that is not i.i.d. In numerical experiments using a large real-world dataset, our meta-learner consistently outperforms state-of-the-art benchmark models. Remarkably, it outperforms task-specific benchmarks, even when applied to new, unseen inventory management tasks.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Maichle et al. "In-Context Quantile Regression for Multi-Product Inventory Management Using Time-Series Transformers." NeurIPS 2024 Workshops: TSALM, 2024.

Markdown

[Maichle et al. "In-Context Quantile Regression for Multi-Product Inventory Management Using Time-Series Transformers." NeurIPS 2024 Workshops: TSALM, 2024.](https://mlanthology.org/neuripsw/2024/maichle2024neuripsw-incontext/)

BibTeX

@inproceedings{maichle2024neuripsw-incontext,
  title     = {{In-Context Quantile Regression for Multi-Product Inventory Management Using Time-Series Transformers}},
  author    = {Maichle, Magnus Josef and Mukherjee, Sohom and Günder, Kai and Antonov, Ivane and Stein, Nikolai and Pibernik, Richard},
  booktitle = {NeurIPS 2024 Workshops: TSALM},
  year      = {2024},
  url       = {https://mlanthology.org/neuripsw/2024/maichle2024neuripsw-incontext/}
}