Advanced search
1 file | 675.59 KB Add to list

Performance of an end-to-end inventory demand forecasting pipeline using a federated data ecosystem

Author
Organization
Abstract
One of the key challenges for (fresh produce) retailers is achieving optimal demand forecasting, as it plays a crucial role in operational decision-making and dampens the Bullwhip Effect. Improved forecasts holds the potential to achieve a balance between minimizing waste and avoiding shortages. Different retailers have partial views on the same products, which—when combined—can improve the forecasting of individual retailers’ inventory demand. However, retailers are hesitant to share all their individual data. Therefore, we propose an end-to-end graph-based time series forecasting pipeline using a federated data ecosystem to predict inventory demand for supply chain retailers. Graph deep learning forecasting has the ability to comprehend intricate relationships, and it seamlessly tunes into the diverse, multi-retailer data present in a federated setup. The system aims to create a unified data view without centralization, addressing technical and operational challenges, which are discussed throughout the text. We test this pipeline using real-world data across large and small retailers, and discuss the performance obtained and how it can be further improved.

Downloads

  • DS786.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 675.59 KB

Citation

Please use this url to cite or link to this publication:

MLA
Moura, Henrique Duarte, et al. “Performance of an End-to-End Inventory Demand Forecasting Pipeline Using a Federated Data Ecosystem.” ENGINEERING PROCEEDINGS, vol. 68, no. 1, 2024, doi:10.3390/engproc2024068033.
APA
Moura, H. D., de Vleeschauwer, E., Haesendonck, G., De Meester, B., D’eer, L., De Schepper, T., … Mannens, E. (2024). Performance of an end-to-end inventory demand forecasting pipeline using a federated data ecosystem. ENGINEERING PROCEEDINGS, 68(1). https://doi.org/10.3390/engproc2024068033
Chicago author-date
Moura, Henrique Duarte, Els de Vleeschauwer, Gerald Haesendonck, Ben De Meester, Lynn D’eer, Tom De Schepper, Siegfried Mercelis, and Erik Mannens. 2024. “Performance of an End-to-End Inventory Demand Forecasting Pipeline Using a Federated Data Ecosystem.” In ENGINEERING PROCEEDINGS. Vol. 68. https://doi.org/10.3390/engproc2024068033.
Chicago author-date (all authors)
Moura, Henrique Duarte, Els de Vleeschauwer, Gerald Haesendonck, Ben De Meester, Lynn D’eer, Tom De Schepper, Siegfried Mercelis, and Erik Mannens. 2024. “Performance of an End-to-End Inventory Demand Forecasting Pipeline Using a Federated Data Ecosystem.” In ENGINEERING PROCEEDINGS. Vol. 68. doi:10.3390/engproc2024068033.
Vancouver
1.
Moura HD, de Vleeschauwer E, Haesendonck G, De Meester B, D’eer L, De Schepper T, et al. Performance of an end-to-end inventory demand forecasting pipeline using a federated data ecosystem. In: ENGINEERING PROCEEDINGS. 2024.
IEEE
[1]
H. D. Moura et al., “Performance of an end-to-end inventory demand forecasting pipeline using a federated data ecosystem,” in ENGINEERING PROCEEDINGS, Gran Canaria, Spain, 2024, vol. 68, no. 1.
@inproceedings{01J2DZCV7F30F3M7YFWMJGCZ2T,
  abstract     = {{One of the key challenges for (fresh produce) retailers is achieving optimal demand forecasting, as it plays a crucial role in operational decision-making and dampens the Bullwhip Effect. Improved forecasts holds the potential to achieve a balance between minimizing waste and avoiding shortages. Different retailers have partial views on the same products, which—when combined—can improve the forecasting of individual retailers’ inventory demand. However, retailers are hesitant to share all their individual data. Therefore, we propose an end-to-end graph-based time series forecasting pipeline using a federated data ecosystem to predict inventory demand for supply chain retailers. Graph deep learning forecasting has the ability to comprehend intricate relationships, and it seamlessly tunes into the diverse, multi-retailer data present in a federated setup. The system aims to create a unified data view without centralization, addressing technical and operational challenges, which are discussed throughout the text. We test this pipeline using real-world data across large and small retailers, and discuss the performance obtained and how it can be further improved.}},
  articleno    = {{33}},
  author       = {{Moura, Henrique Duarte and de Vleeschauwer, Els and Haesendonck, Gerald and De Meester, Ben and D'eer, Lynn and De Schepper, Tom and Mercelis, Siegfried and Mannens, Erik}},
  booktitle    = {{ENGINEERING PROCEEDINGS}},
  issn         = {{2673-4591}},
  language     = {{eng}},
  location     = {{Gran Canaria, Spain}},
  number       = {{1}},
  pages        = {{10}},
  title        = {{Performance of an end-to-end inventory demand forecasting pipeline using a federated data ecosystem}},
  url          = {{http://doi.org/10.3390/engproc2024068033}},
  volume       = {{68}},
  year         = {{2024}},
}

Altmetric
View in Altmetric