Better Documentation for combining different models (MLforecast + statsforecast for example)

[jan-voids]

Description

The given examples are working, but I find it hard to setup more advanced frameworks where I want to combine separate models, which I trained individually. Especially the usage of the correct indexing can be tricky.

Link

No response

[elephaint]

I think you're right - what would such an example look like in your case?

Maybe we can start with an existing example and fit it to your needs? (i.e. using multiple models?)

[jan-voids]

If we take the point reconciliation (tourism) example, it would be cool to show how a model from the mlforcast family on a lower level (e.g.: region) can be combined with statsforecast models for higher levels.

Another question is if (and how) to combine different time levels (but might be for a different issue, not sure).