https://github.com/nixtla logo
#neural-forecast
Title
# neural-forecast
s

Stefan Wiegand

08/28/2023, 3:28 PM
Dear Nixla Team, I have a question regarding normalization/scaling of different features. If I select a model that allows exogenous variables, say NBEATSx and I select a Scaler say minmax1. Is this Scaler applied to y only or to the exogenous vars aswell? Exogenous vars maybe of very different type e.g. int or booleans that I would not like to be normalized at all (because they have time invariant meaning that I do not want messed up) or time series, which I would like to have normalized. Is there a way to control how each input is normalized?
c

Cristian (Nixtla)

08/28/2023, 4:37 PM
Hi @Stefan Wiegand. Scalers are applied to all temporal variables (
y
,
hist_egox_list
, and
futr_exog_list
). There is currently no way of controlling which variables to normalize. In our experience, normalizing booleans does not affect performance (for
nf
models)
s

Stefan Wiegand

08/28/2023, 4:59 PM
Great! Thanks alot for your quick response!
2 Views