Class-Focused Variable Importance in Random Forests for Multi-Class Outcomes
Journal of Classification · 2026-07 · 43 (2) · 433-457
DOI: 10.1007/s00357-026-09545-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Classification, online erschienen am 04.03.2026. Verfasst von Roman Hornung und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Ludwig-Maximilians-Universität München.
Abstract (Originalsprache)
In multi-class prediction tasks with interpretative goals, covariates that help distinguish individual classes, termed “class-related covariates,” can be of particular interest. Conventional variable importance measures (VIMs) from random forests, such as permutation and Gini importance, rank covariates by overall predictive contribution and thus also assign high importance to covariates that differentiate between groups of classes. We propose a novel VIM, the class-focused VIM, which ranks covariates by their ability to distinguish individual outcome classes. It evaluates covariates using hypothetical multi-way class-based partitions at each node, without altering tree construction. As a complement, we introduce the discriminatory VIM, which measures general covariate influence based on the actual node splits. Simulations show that, unlike conventional VIMs, the class-focused VIM specifically ranks class-related covariates high. Real data examples illustrate how both suggested VIMs behave on real datasets and how their results can be interpreted.
Förderung
- Deutsche Forschungsgemeinschaft
- Ludwig-Maximilians-Universität München
Zitieren
APA
Hornung, R., & Hapfelmeier, A. (2026). Class-Focused Variable Importance in Random Forests for Multi-Class Outcomes. Journal of Classification, 43(2), 433-457. https://doi.org/10.1007/s00357-026-09545-6
Vancouver
Hornung R, Hapfelmeier A. Class-Focused Variable Importance in Random Forests for Multi-Class Outcomes. Journal of Classification. 2026;43(2):433-457. doi:10.1007/s00357-026-09545-6
BibTeX
@article{Hornung2026,
author = {Hornung, Roman and Hapfelmeier, Alexander},
title = {Class-Focused Variable Importance in Random Forests for Multi-Class Outcomes},
journal = {Journal of Classification},
year = {2026},
volume = {43},
number = {2},
pages = {433--457},
doi = {10.1007/s00357-026-09545-6}
}
EUVIMED