Skip to content

Latest commit

 

History

History
30 lines (21 loc) · 834 Bytes

README.md

File metadata and controls

30 lines (21 loc) · 834 Bytes

PROFHiT: Probabilistic Robust Forecasting for Hierarchical Time-series

Setup

  1. Make sure anaconda or miniconda is installed.
  2. Pachake required are listed in conda.yml.
  3. Run the following command to install the required packages.
bash scripts/setup.sh

Running

For Tourism dataset run train_tourism.py and train.py for others. The start of the script has hyperparameters including the dataset to use.

Citation

If you find this work useful for your research please cite us as follows:

@article{kamarthi2022profhit,
  title={PROFHIT: Probabilistic Robust Forecasting for Hierarchical Time-series},
  author={Kamarthi, Harshavardhan and Kong, Lingkai and Rodr{\'\i}guez, Alexander and Zhang, Chao and Prakash, B Aditya},
  journal={arXiv preprint arXiv:2206.07940},
  year={2022}
}