A Configurable Framework for Quantifying and Comparing Interpretability Across ML Models and Methods
Machine Learning and Knowledge Extraction · 19.08.2026 · 8 (8) · 250
DOI: 10.3390/make8080250 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 19.08.2026. Verfasst von Batu Kaan Özen und 2 weiteren Autor:innen. Die Arbeit nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry for Economic Affairs and Climate Action.
Abstract (Originalsprache)
Machine learning (ML) models have achieved remarkable success in areas ranging from healthcare to autonomous systems. Yet, their inherent complexity frequently obscures the reasoning behind their decisions, undermining transparency, accountability, and user trust. Compounding this issue is the absence of a universal methodology for comparing and ranking interpretability across diverse ML models and interpretability techniques. This paper addresses this gap by introducing a configurable framework of quantitative metrics to evaluate and rank interpretability. Our approach offers a structured, heuristic basis for assessing model clarity, decision logic, and accessibility, enabling practitioners to systematically compare interpretability across a wide range of algorithms and techniques. The resulting scores are intended as a practical, domain-configurable heuristic guide for comparison rather than a universal notion of interpretability.
Förderung
- German Federal Ministry for Economic Affairs and Climate Action
Zitieren
APA
Özen, B. K., Waschulzik, T., & Knoll, A. (2026). A Configurable Framework for Quantifying and Comparing Interpretability Across ML Models and Methods. Machine Learning and Knowledge Extraction, 8(8), 250. https://doi.org/10.3390/make8080250
Vancouver
Özen BK, Waschulzik T, Knoll A. A Configurable Framework for Quantifying and Comparing Interpretability Across ML Models and Methods. Machine Learning and Knowledge Extraction. 2026;8(8):250. doi:10.3390/make8080250
BibTeX
@article{zen2026,
author = {Özen, Batu Kaan and Waschulzik, Thomas and Knoll, Alois},
title = {A Configurable Framework for Quantifying and Comparing Interpretability Across ML Models and Methods},
journal = {Machine Learning and Knowledge Extraction},
year = {2026},
volume = {8},
number = {8},
pages = {250},
doi = {10.3390/make8080250}
}
EUVIMED