EUVIMEDEUVIMED entdecken
Crossref

LMGL-WD: LLM-Guided Multi-Task Graph Learning for Category-Level Warehouse Demand Prediction in E-Commerce

Wenjun Lyu, Fangyu Li, Yudong Zhang, Shuai Wang, Yunhuai Liu, Tian He, Desheng Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15492-15500

DOI: 10.1609/aaai.v40i18.38577 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wenjun Lyu und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In warehouse-based e-commerce, accurate category-level warehouse demand prediction is essential to ensure effective inventory management. Existing works mainly explore advanced time series models to capture the temporal dynamics, failing to mine cross-category and cross-warehouse correlations effectively. In this paper, we explore large language models to understand the semantic information and fuse multi-view knowledge to enhance demand prediction. However, it is not trivial due to: i) the inaccurate LLM’s understanding of the category-related and warehouse-related textual input; and ii) the complicated cross-warehouse knowledge utilization. To solve the above challenges, we propose an LLM-guided multi-task graph learning framework, LMGL-WD, for category-level warehouse demand prediction. Specifically, LMGL-WD includes three components: i) an LLM-guided category series encoding module to represent each category through contextual and series embedding; ii) a cross-warehouse category learning module to adaptively mine the informative knowledge from cross warehouses to enhance category representation; and iii) a cross-category multi-task learning module to adaptively capture cross-category correlations to improve demand prediction. Extensive evaluation results with real-world data collected from one of the largest e-commerce platforms in China demonstrate that LMGL-WD achieves superior performance, e.g., reduces MAPE by up to 31.59%, compared to state-of-the-art methods.

Zitieren

APA

Lyu, W., Li, F., Zhang, Y., Wang, S., Liu, Y., He, T., & Zhang, D. (2026). LMGL-WD: LLM-Guided Multi-Task Graph Learning for Category-Level Warehouse Demand Prediction in E-Commerce. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15492-15500. https://doi.org/10.1609/aaai.v40i18.38577

Vancouver

Lyu W, Li F, Zhang Y, Wang S, Liu Y, He T, et al. LMGL-WD: LLM-Guided Multi-Task Graph Learning for Category-Level Warehouse Demand Prediction in E-Commerce. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15492-15500. doi:10.1609/aaai.v40i18.38577

BibTeX
@article{Lyu2026,
  author = {Lyu, Wenjun and Li, Fangyu and Zhang, Yudong and Wang, Shuai and Liu, Yunhuai and He, Tian and Zhang, Desheng},
  title = {LMGL-WD: LLM-Guided Multi-Task Graph Learning for Category-Level Warehouse Demand Prediction in E-Commerce},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15492--15500},
  doi = {10.1609/aaai.v40i18.38577}
}
Kostenlos starten →