0
$\begingroup$

Since there are many references that a RF uses a slightly different approach on splitting a node in comparison to Vanilla Bagging. Does Gini index play an active role in the split or it's just another index like Information Gain to measure the improvement of the uncertainty from one node to a next?

$\endgroup$
1
$\begingroup$

Definitely yes, it is one of the many criteria you can set in the tuning to determine a split in the node. Of course it depends on the type of problem you face. If you need this is a good explanation of RF

$\endgroup$
  • $\begingroup$ What happens in case we examine unlabeled data (unsupervised learning)? In that case do we use Bagging also for node splitting instead of Gini index? $\endgroup$ – Christos K. Feb 8 at 20:25
  • $\begingroup$ Gini index measures the heterogeneity of a group. If you try to make groups on the base of a particular feature well yes, it can also be used for UL. $\endgroup$ – 3nomis Feb 9 at 16:58

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.