GRATIS: GeneRAting TIme Series with diverse and controllable characteristics

10 September 2021
YouTube

 Download pdf

ADSN Focused Workshop: Synthetic Data

Synthetic time series are useful for benchmarking and testing methods for forecasting, clustering, classification and other tasks. I will discuss an approach to this where we can generate time series with diverse and controllable characteristics using mixture autoregressive (MAR) models. This can be done with the gratis package for R.


« Uncertain futures: what can we forecast and when should we give up? | The geometry of forecast reconciliation »