EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Task Temporal Fusion Transformer for Joint Sales and Inventory Forecasting in Amazon E-Commerce Supply Chain

Zheqi Hu, Yiwen Hu, Hanwu Li

Journal of Computer, Signal, and System Research · 25.02.2026 · 3 (2) · 47-55

DOI: 10.71222/7axx7m73 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computer, Signal, and System Research, online erschienen am 25.02.2026. Verfasst von Zheqi Hu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efficient inventory management and accurate sales forecasting are critical challenges in large-scale e-commerce platforms such as Amazon, where stockouts and overstocking can lead to substantial financial losses and operational inefficiencies. Traditional single-task forecasting models, which focus solely on sales or inventory, often fail to capture the complex temporal dependencies and cross-task interactions that characterize real-world supply chain dynamics. To address this limitation, this study proposes a Multi-Task Temporal Fusion Transformer (TFT-MTL) framework designed for joint sales and inventory forecasting within the Amazon e-commerce ecosystem. The model integrates heterogeneous data sources-including historical sales records, warehouse inventory levels, pricing, promotions, and event-driven factors such as holidays and Prime Day campaigns-through a unified deep learning architecture. A shared encoder captures long-term temporal patterns, while task-specific decoder heads predict sales volume, inventory turnover, and stockout probability simultaneously. Experiments on large-scale real-world datasets demonstrate that the proposed TFT-MTL model significantly outperforms baseline methods such as LSTM, GRU, and single-task TFT. Compared with the single-task TFT model, the proposed approach achieves a 6.2% reduction in Sales RMSE, a 12.7% decrease in Sales MAPE, a 6.4% reduction in Inventory RMSE, and a 12.4% decrease in Inventory MAPE. These results confirm the model's ability to effectively capture multi-dimensional dependencies across supply chain variables. The proposed framework provides an interpretable, data-driven decision support tool for optimizing Amazon's inventory scheduling and demand planning strategies.

Zitieren

APA

Hu, Z., Hu, Y., & Li, H. (2026). Multi-Task Temporal Fusion Transformer for Joint Sales and Inventory Forecasting in Amazon E-Commerce Supply Chain. Journal of Computer, Signal, and System Research, 3(2), 47-55. https://doi.org/10.71222/7axx7m73

Vancouver

Hu Z, Hu Y, Li H. Multi-Task Temporal Fusion Transformer for Joint Sales and Inventory Forecasting in Amazon E-Commerce Supply Chain. Journal of Computer, Signal, and System Research. 2026;3(2):47-55. doi:10.71222/7axx7m73

BibTeX
@article{Hu2026,
  author = {Hu, Zheqi and Hu, Yiwen and Li, Hanwu},
  title = {Multi-Task Temporal Fusion Transformer for Joint Sales and Inventory Forecasting in Amazon E-Commerce Supply Chain},
  journal = {Journal of Computer, Signal, and System Research},
  year = {2026},
  volume = {3},
  number = {2},
  pages = {47--55},
  doi = {10.71222/7axx7m73}
}
Kostenlos starten →