Decision Tree Splitting Criterion

Medium

machine-learning Amazon Microsoft LinkedIn

When building a decision tree for a binary classification problem, you must choose a splitting criterion. In practice, which statement about Gini impurity and information gain (entropy) is most accurate?

Multiple Choice

Entropy always produces deeper, more accurate trees than Gini impurity Gini impurity and entropy typically yield similar results, with Gini being computationally cheaper Gini impurity is only suitable for multi-class problems, not binary classification Entropy requires feature scaling while Gini impurity does not

Correct!

Incorrect — try again next time!

Upgrade to Pro to unlock solutions and explanations

Decision Tree Splitting Criterion

Multiple Choice

Related problems

Deep-dive guides