[isoprophlex]

Because they're so cheap to train, you can just use n models if you want to predict n steps ahead.

In sklearn, if you have a single-output regressor, use this for ergonomics: https://scikit-learn.org/stable/modules/generated/sklearn.mu...

The added benefit is that you optimize each regressor towards its own target timestep t+1 ... t+n. A single loss on the aggregate of all timesteps is often problematic

[aldanor]

There's been recent advances in joint fitting of multi-output regression forests ("vector leaf"): https://xgboost.readthedocs.io/en/stable/tutorials/multioutp...

In theory, this might suit the multi-step forecast use case.