A random forest guided tour

The random forest algorithm, proposed by L. Breiman in 2001, has been extremely successful as a general-purpose classification and regression method. The approach, which combines several randomized decision trees and aggregates their predictions by averaging, has shown excellent performance in setti...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Test (Madrid, Spain) Jg. 25; H. 2; S. 197 - 227
Hauptverfasser: Biau, Gérard, Scornet, Erwan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2016
Springer Nature B.V
Spanish Society of Statistics and Operations Research/Springer
Schlagworte:
Aggregates
Algorithms
Classification
Datasets
Decision trees
Distance learning
Economics
Finance
Insurance
Invited Paper
Learning
Management
Mathematical analysis
Mathematics
Mathematics and Statistics
Regression
Regression analysis
Statistical Theory and Methods
Statistics
Statistics for Business
Studies
Survival analysis
Tasks
United States > US
Randomization
Resampling
Variable importance
62G02
Parameter tuning
Random forests
ISSN:1133-0686, 1863-8260
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The random forest algorithm, proposed by L. Breiman in 2001, has been extremely successful as a general-purpose classification and regression method. The approach, which combines several randomized decision trees and aggregates their predictions by averaging, has shown excellent performance in settings where the number of variables is much larger than the number of observations. Moreover, it is versatile enough to be applied to large-scale problems, is easily adapted to various ad hoc learning tasks, and returns measures of variable importance. The present article reviews the most recent theoretical and methodological developments for random forests. Emphasis is placed on the mathematical forces driving the algorithm, with special attention given to the selection of parameters, the resampling mechanism, and variable importance measures. This review is intended to provide non-experts easy access to the main ideas.
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:1133-0686
1863-8260
DOI:10.1007/s11749-016-0481-7