Transfer learning for hierarchical forecasting: Reducing computational efforts of M5 winning method

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.