A1 Journal article (refereed)
Comparison of feature importance measures as explanations for classification models (2021)
Saarela, M., & Jauhiainen, S. (2021). Comparison of feature importance measures as explanations for classification models. SN Applied Sciences, 3(2), Article 272. https://doi.org/10.1007/s42452-021-04148-9
JYU authors or editors
Publication details
All authors or editors: Saarela, Mirka; Jauhiainen, Susanne
Journal or series: SN Applied Sciences
ISSN: 2523-3963
eISSN: 2523-3971
Publication year: 2021
Volume: 3
Issue number: 2
Article number: 272
Publisher: Springer
Publication country: Germany
Publication language: English
DOI: https://doi.org/10.1007/s42452-021-04148-9
Publication open access: Openly available
Publication channel open access: Partially open access channel
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/74012
Abstract
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.
Keywords: machine learning; artificial intelligence; classification
Free keywords: feature importance; explainable artificial intelligence; interpretable models; random forest; logistic regression
Contributing organizations
Related projects
- Competitive funding to strengthen universities’ research profiles. Profiling actions at the JYU, round 3
- Hämäläinen, Keijo
- Research Council of Finland
Ministry reporting: Yes
Reporting Year: 2021
JUFO rating: 1