Why ROC-AUC Is Misleading for Highly Imbalanced Data: In-Depth Evaluation of MCC, F2-Score, H-Measure, and AUC-Based Metrics Across Diverse Classifiers
Technologies · 10.01.2026 · 14 (1) · 54
DOI: 10.3390/technologies14010054 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technologies, online erschienen am 10.01.2026. Verfasst von Mehdi Imani und 3 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study re-evaluates ROC-AUC for binary classification under severe class imbalance (
Zitieren
APA
Imani, M., Joudaki, M., Bagheri, A., & Arabnia, H. R. (2026). Why ROC-AUC Is Misleading for Highly Imbalanced Data: In-Depth Evaluation of MCC, F2-Score, H-Measure, and AUC-Based Metrics Across Diverse Classifiers. Technologies, 14(1), 54. https://doi.org/10.3390/technologies14010054
Vancouver
Imani M, Joudaki M, Bagheri A, Arabnia HR. Why ROC-AUC Is Misleading for Highly Imbalanced Data: In-Depth Evaluation of MCC, F2-Score, H-Measure, and AUC-Based Metrics Across Diverse Classifiers. Technologies. 2026;14(1):54. doi:10.3390/technologies14010054
BibTeX
@article{Imani2026,
author = {Imani, Mehdi and Joudaki, Majid and Bagheri, Ayoub and Arabnia, Hamid R.},
title = {Why ROC-AUC Is Misleading for Highly Imbalanced Data: In-Depth Evaluation of MCC, F2-Score, H-Measure, and AUC-Based Metrics Across Diverse Classifiers},
journal = {Technologies},
year = {2026},
volume = {14},
number = {1},
pages = {54},
doi = {10.3390/technologies14010054}
}
EUVIMED