Change search
ReferencesLink to record
Permanent link

Direct link
Forests of probability estimation trees
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
2012 (English)In: International journal of pattern recognition and artificial intelligence, ISSN 0218-0014, Vol. 26, no 2, 1251001- p.Article in journal (Refereed) Published
Abstract [en]

Probability estimation trees (PETs) generalize classification trees in that they assign class probability distributions instead of class labels to examples that are to be classified. This property has been demonstrated to allow PETs to outperform classification trees with respect to ranking performance, as measured by the area under the ROC curve (AUC). It has further been shown that the use of probability correction improves the performance of PETs. This has lead to the use of probability correction also in forests of PETs. However, it was recently observed that probability correction may in fact deteriorate performance of forests of PETs. A more detailed study of the phenomenon is presented and the reasons behind this observation are analyzed. An empirical investigation is presented, comparing forests of classification trees to forests of both corrected and uncorrected PETS on 34 data sets from the UCI repository. The experiment shows that a small forest (10 trees) of probability corrected PETs gives a higher AUC than a similar-sized forest of classification trees, hence providing evidence in favor of using forests of probability corrected PETs. However, the picture changes when increasing the forest size, as the AUC is no longer improved by probability correction. For accuracy and squared error of predicted class probabilities (Brier score), probability correction even leads to a negative effect. An analysis of the mean squared error of the trees in the forests and their variance, shows that although probability correction results in trees that are more correct on average, the variance is reduced at the same time, leading to an overall loss of performance for larger forests. The main conclusions are that probability correction should only be employed in small forests of PETs, and that for larger forests, classification trees and PETs are equally good alternatives.

Place, publisher, year, edition, pages
2012. Vol. 26, no 2, 1251001- p.
Keyword [en]
Random forests, probability estimation trees, accuracy, area under ROC curve, Brier score
National Category
Remote Sensing
URN: urn:nbn:se:su:diva-81799DOI: 10.1142/S0218001412510019ISI: 000308104300002OAI: diva2:567515


Available from: 2012-11-13 Created: 2012-11-01 Last updated: 2012-11-13Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Boström, Henrik
By organisation
Department of Computer and Systems Sciences
In the same journal
International journal of pattern recognition and artificial intelligence
Remote Sensing

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 82 hits
ReferencesLink to record
Permanent link

Direct link