This message was deleted.

Hi. Each package has its own scope, the main differences are: • statsforecast: ◦ mainly statistical models ◦ one model per serie • mlforecast ◦ ML (sklearn-compatible) models ◦ one model for all series

Hi @Matías Benedetto, you don't have to choose wither or. You can leverage both. Here is a tutorial on how to combina them: https://nixtla.github.io/statsforecast/docs/tutorials/statisticalneuralmethods.html

that is really useful @Max (Nixtla), thank you for sharing

Thanks to you :)