Transfer learning for hierarchical forecasting: Reducing computational efforts of M5 winning method
Wellens, Arnoud P. Udenio, Maxi Boute, Robert
Wellens, Arnoud P.
Udenio, Maxi
Boute, Robert
Citations
Altmetric:
Publication Type
Journal article with impact factor
Editor
Supervisor
Publication Year
2022
Journal
International Journal of Forecasting
Book
Publication Volume
38
Publication Issue
4
Publication Begin page
1482
Publication End page
1491
Publication Number of pages
Collections
Abstract
The winning machine learning methods of the M5 Accuracy competition demonstrated high levels of forecast accuracy compared to the top-performing benchmarks in the history of the Mcompetitions. Yet, large-scale adoption is hampered due to the signi cant computational requirements to model, tune, and train these state-of-the-art algorithms. To overcome this major issue, we discuss the potential of transfer learning (TL) to reduce the computational e ort in hierarchical forecasting and provide proof of concept that TL can be applied on M5 top-performing methods. We demonstrate our easy-to-use TL framework on the recursive store level LightGBM models of the M5 winning method and attain similar levels of forecast accuracy with roughly 25% less training time. Our ndings provide evidence for a novel application of TL to facilitate practical applicability of the M5 winning methods in large-scale settings with hierarchically structured data.
Research Projects
Organizational Units
Journal Issue
Keywords
M5 Accuracy Competition, Computational Requirements, Transfer Learning, LightGBM, Hierarchical Forecasting