Announcing the winners & finalists of the Dataiku Frontrunner Awards 2021! Read their inspiring stories

Biased Random Forest Feature Importance

Level 1
Biased Random Forest Feature Importance

In the following article, it is stated that the Feature Importance of Random Forests can be biased towards continuous variables. If I understand correctly DataIKU uses the standard scikit-learn FI, also when other models are used as explained here:

What is your opinion on this article and if you agree that the FI is biased, do you have a solution within DataIKU?

0 Kudos
0 Replies
A banner prompting to get Dataiku DSS