-
Notifications
You must be signed in to change notification settings - Fork 6
Open
Description
Dear organizers!
What is the motivation for choosing such metrics, as Paerson correlation, etc, when there are commonly used, classic metrics for regressor quality estimations - explained variance score, mean squared error, r2 score...?
I tried myself to compare the modelling results by classic metrics and by metrics provided - and the ranking of different regression models with two approaches is different.
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels