Degenerate Hierarchical Time Series Reconciliation

Takes the MinT implementation of the 'hts'< https://cran.r-project.org/package=hts> package and adapts it to allow degenerate hierarchical structures. Instead of the "nodes" argument, this function takes an S matrix which is more versatile in the structures it allows. For a demo, see Steinmeister and Pauly (2024). The MinT algorithm is based on Wickramasuriya et al. (2019).

htsDegenerateR

htsDegenerateR adapts the original hts library implementation of the trace minimization algorithm originally proposed by Wickramasuriya et al..

This library can be installed using:

devtools::install_github("lsteinmeister/htsDegenerateR“)

For more details, see Steinmeister et al..

Citation

Please cite this library as follows:

Steinmeister, L., & Pauly, M. (2024). Degenerate Hierarchical Time Series Reconciliation With The Minimum Trace Algorithm in R. In D. Herberger & M. Hübner (Eds.), Proceedings of the Conference on Production Systems and Logistics: CPSL. publish-Ing. https://doi.org/https://doi.org/10.15488/17729

References

Steinmeister, L., & Pauly, M. (2024). Degenerate Hierarchical Time Series Reconciliation With The Minimum Trace Algorithm in R. In D. Herberger & M. Hübner (Eds.), Proceedings of the Conference on Production Systems and Logistics: CPSL. publish-Ing. https://doi.org/https://doi.org/10.15488/17729

Wickramasuriya, S. L., Athanasopoulos, G., & Hyndman, R. J. (2019). Optimal Forecast Reconciliation for Hierarchical and Grouped Time Series Through Trace Minimization. Journal of the American Statistical Association, 114(526), 804–819. https://doi.org/10.1080/01621459.2018.1448825