Improving forecast stability with deep learning
_{Jente Van Belle, Ruben Crevits, Wouter Verbeke [2023]}

Improving forecast stability using deep learning. International Journal of Forecasting.
See https://www.sciencedirect.com/science/article/pii/S016920702200098X.

The code has been developed by Jente Van Belle, Ph.D. The PyTorch implementation of N-BEATS (Oreshkin, B. N., Carpov, D., Chapados, N., & Bengio, Y. (2019). N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. See https://arxiv.org/abs/1905.10437.) developed by Philippe Remy (https://github.com/philipperemy/n-beats) was used as a starting point.

If you experience any problems, you can contact Jente Van Belle via jente.vanbelle@kuleuven.be.

Citing

Please cite our paper and/or code as follows:

@article{van2023,
  title={Improving forecast stability using deep learning},
  author={Van Belle, Jente and Crevits, Ruben and Verbeke, Wouter},
  journal={International Journal of Forecasting},
  volume={39},
  number={3},
  pages={1333--1350},
  year={2023},
  publisher={Elsevier}
}