This message was deleted.

I am asking because MSTL is part of statsforecast library already so I wonder if there is something built in. Thanks :)

Hey, thanks for the kind words. There's no built-in way at the moment but we've thought of supporting target transforms that take statsforecast models. Would your use case involve fitting the MSTL, subtracting its prediction from the current target and passing that to mlforecast?

yes something along those lines or perhaps have MSTL in the tsfeatures to generate seasonal component that can then be used as lagged feature, etc.