Technical note: Some properties of splitting criteria
Various criteria have been proposed for deciding which split is best at a given node of a binary classification tree. Consider the question: given a goodness-of-split criterion and the class populations of the instances at a node, what distribution of the instances between the two children nodes max...
Gespeichert in:
Veröffentlicht in: | Machine learning 1996-07, Vol.24 (1), p.41-47 |
---|---|
1. Verfasser: | |
Format: | Artikel |
Sprache: | eng |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Various criteria have been proposed for deciding which split is best at a given node of a binary classification tree. Consider the question: given a goodness-of-split criterion and the class populations of the instances at a node, what distribution of the instances between the two children nodes maximizes the goodness-of-split criterion? The answers reveal an interesting distinction between the gini and entropy criterion. |
---|---|
ISSN: | 0885-6125 1573-0565 |
DOI: | 10.1007/BF00117831 |