Glossary term
Glossary term
Foundations
Any endpoint in a decision tree. Unlike a condition, a leaf doesn't perform a test. Rather, a leaf is a possible prediction. A leaf is also the terminal node of an inference path.
For example, the following decision tree contains three leaves:

See Decision trees in the Decision Forests course for more information.
For example, the following decision tree contains three leaves:
See Decision trees in the Decision Forests course for more information.
Created for this library
A risk modeling team uses small minimum-leaf sizes in its decision tree to capture rare default patterns without overfitting.
A retail demand team uses larger minimum-leaf sizes to keep tree splits robust on small store-week-SKU samples.
A churn modeling team monitors leaf-level error rates to investigate which decision-tree branches misclassify most often.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License