The BATS model is a time series model for series exhibiting multiple seasonalities. It is a generalization of the traditional seasonal innovations models.
The BATS model was introduced by De Livera, Hyndman & Snyder (2011, JASA). "BATS" is an acronym denoting its salient features:
- B for Box-Cox transformations
- A for ARMA errors
- T for trend
- S for seasonality
The BATS model is related to the TBATS model. It can be fitted using the
bats() command in the
forecast package for R.