Bagging Predictors

by: Leo Breiman

edited by: Ross Quinlan

Machine Learning, Vol. 24, No. 2. (1996), pp. 123-140.

View FullText article

DOI, MetaPress

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

gabe_rosser, drivard, sona, ngarera, maheshj

Find related articles with these CiteULike tags

aggregating, aggregation, averaging, bagging, bootstrap, classifier_ensemble, combining, ensembles, learning, machine_learning, predictor, regression, survey

Abstract

Bagging predictors is a method for generating multiple versions of a predictor and using these to get an aggregated predictor. The aggregation averages over the versions when predicting a numerical outcome and does a plurality vote when predicting a class. The multiple versions are formed by making bootstrap replicates of the learning set and using these as new learning sets. Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy. The vital element is the instability of the prediction method. If perturbing the learning set can cause significant changes in the predictor constructed, then bagging can improve accuracy.

@article{breiman_1996_ml, abstract = {Bagging predictors is a method for generating multiple versions of a predictor and using these to get an aggregated predictor. The aggregation averages over the versions when predicting a numerical outcome and does a plurality vote when predicting a class. The multiple versions are formed by making bootstrap replicates of the learning set and using these as new learning sets. Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy. The vital element is the instability of the prediction method. If perturbing the learning set can cause significant changes in the predictor constructed, then bagging can improve accuracy.}, address = {Boston}, author = {Breiman, Leo }, citeulike-article-id = {315762}, doi = {10.1023/A:1018054314350}, editor = {Quinlan, Ross }, journal = {Machine Learning}, keywords = {classifier\_ensemble}, number = {2}, pages = {123--140}, posted-at = {2008-06-25 18:20:31}, priority = {0}, publisher = {Kluwer Academic Publishers}, title = {Bagging Predictors}, url = {http://dx.doi.org/10.1023/A:1018054314350}, volume = {24}, year = {1996} }

RIS record

TY - JOUR ID - breiman_1996_ml L3 - citeulike-article-id:315762 TI - Bagging Predictors JF - Machine Learning VL - 24 IS - 2 SP - 123 EP - 140 AD - Boston PB - Kluwer Academic Publishers N2 - Bagging predictors is a method for generating multiple versions of a predictor and using these to get an aggregated predictor. The aggregation averages over the versions when predicting a numerical outcome and does a plurality vote when predicting a class. The multiple versions are formed by making bootstrap replicates of the learning set and using these as new learning sets. Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy. The vital element is the instability of the prediction method. If perturbing the learning set can cause significant changes in the predictor constructed, then bagging can improve accuracy. KW - classifier_ensemble AU - Breiman, Leo A2 - Quinlan, Ross PY - 1996/// UR - http://dx.doi.org/10.1023/A:1018054314350 ER -

RIS BibTeX