Please enable JavaScript.
Coggle requires JavaScript to display documents.
Larsen Chapter 20 & 22 (20.6 Features to Utilize (Mutable features:…
Larsen Chapter 20 & 22
-
20.1 Unlocking Holdout
Release holdout data to ensure that there haven't been any mistakes made in the model creation process (it is untouched data)
If the ranking differences between Cross Validation and Holdout are minimal, this is a GOOD model. If holdout sample scores are substantially lower than the cross validation sample, there is a problem.
-
-
-
-