Comparison of feature importance measures as explanations for classification models
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
Published inSN Applied Sciences
© 2021 the Authors
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. ...
Publication in research information system
MetadataShow full item record
Related funder(s)Academy of Finland
Funding program(s)Research profiles, AoF
Additional information about fundingThis research was supported by the Academy of Finland (Grant No. 311877) and is related to the thematic research area DEMO (Decision Analytics Utilizing Causal Models and Multiobjective Optimization, jyu.fi/demo) of the University of Jyväskylä, Finland.
Showing items with similar title or keywords.
Prezja, Fabi (2018)In the field of artificial intelligence, supervised machine learning enables us to try to develop automatic recognition systems. In music information retrieval, training and testing such systems is possible with a variety ...
Comparing the forecasting performance of logistic regression and random forest models in criminal recidivism Aaltonen, Olli-Pekka (2016)Rikosseuraamusalalla on viime vuosina kehitetty uusintarikollisuutta ennustavia malleja (Tyni, 2015), jotka perustuvat tyypillisesti rekisteripohjaisiin mittareihin, jotka mittaavat mm. tuomitun sukupuolta, ikää, rikostaustaa ...
Skrypnyk, Iryna (University of Jyväskylä, 2011)
Terziyan, Vagan; Vitko, Oleksandra (Elsevier, 2022)Artificial Intelligence is an important asset of Industry 4.0. Current discoveries within machine learning and particularly in deep learning enable qualitative change within the industrial processes, applications, systems ...
Misitano, Giovanni; Afsar, Bekir; Lárraga, Giomara; Miettinen, Kaisa (Springer Science and Business Media LLC, 2022)In interactive multiobjective optimization methods, the preferences of a decision maker are incorporated in a solution process to find solutions of interest for problems with multiple conflicting objectives. Since multiple ...