Comparison of feature importance measures as explanations for classification models

• Published in: SN applied sciences Vol. 3; no. 2; p. 272
• Main Authors: Saarela, Mirka, Jauhiainen, Susanne
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.02.2021; Springer Nature B.V
• Subjects: Applied and Technical Physics; Archives & records; Artificial intelligence; Breast cancer; Chemistry/Food Science; Classification; Datasets; Earth Sciences; Engineering; Engineering: Smart Information and Communication Technologies; Environment; Explainable artificial intelligence; Feature selection; Machine learning; Materials Science; Medical research; Regression analysis; Research Article; Explainable artificial intelligence; Feature importance; Logistic regression; Random forest; Interpretable models
• DOI: 10.1007/s42452-021-04148-9
• ISSN: 2523-3963

Explainable artificial intelligence is an emerging research direction helping the user or developer of machine learning models understand why models behave the way they do. The most popular explanation technique is feature importance. However, there are several different approaches how feature importances are being measured, most notably global and local. In this study we compare different feature importance measures using both linear (logistic regression with L1 penalization) and non-linear (random forest) methods and local interpretable model-agnostic explanations on top of them. These methods are applied to two datasets from the medical domain, the openly available breast cancer data from the UCI Archive and a recently collected running injury data. Our results show that the most important features differ depending on the technique. We argue that a combination of several explanation techniques could provide more reliable and trustworthy results. In particular, local explanations should be used in the most critical cases such as false negatives.