Reevaluating feature importance in machine learning: concerns regarding SHAP interpretations in the context of the EU artificial intelligence act

This paper critically examines the analysis conducted by Maußner et al. on AI analysis, particularly their interpretation of feature importances derived from various machine learning models using SHAP (SHapley Additive exPlanations). Although SHAP aids in interpretability, it is subject to model-spe...

Full description

Saved in:
Bibliographic Details
Published inWater research (Oxford) Vol. 280; p. 123514
Main Author Takefuji, Yoshiyasu
Format Journal Article
LanguageEnglish
Published England Elsevier Ltd 15.07.2025
Subjects
Artificial Intelligence
Bias mitigation
EU Artificial intelligence act
European Union
Feature importance
Machine Learning
SHAP
Statistical methods
Feature importance
Bias mitigation
SHAP
Statistical methods
EU Artificial intelligence act
Machine learning
Online AccessGet full text

Cover

More Information
Summary:This paper critically examines the analysis conducted by Maußner et al. on AI analysis, particularly their interpretation of feature importances derived from various machine learning models using SHAP (SHapley Additive exPlanations). Although SHAP aids in interpretability, it is subject to model-specific biases that can misrepresent relationships between variables. The paper emphasizes the lack of ground truth values in feature importance assessments and calls for careful consideration of statistical methodologies, including robust nonparametric approaches. By advocating for the use of Spearman's correlation with p-values and Kendall's tau with p-values, this work aims to strengthen the integrity of findings in machine learning studies, ensuring that conclusions drawn are reliable and actionable.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0043-1354
1879-2448
1879-2448
DOI:10.1016/j.watres.2025.123514