GAM(e) changer or not? An evaluation of interpretable machine learning models based on additive model constraints
Zschech P, Weinzierl S, Hambauer N, Zilker S, Kraus M (2022)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2022
Publisher: AISeL
Pages Range: 1-18
Conference Proceedings Title: Proceedings of the 30th European Conference on Information Systems
Event location: Timisoara
Abstract
The number of information systems (IS) studies dealing with explainable artificial intelligence (XAI) is currently exploding as the field demands more transparency about the internal decision logic of machine learning (ML) models. However, most techniques subsumed under XAI provide post-hoc-analytical explanations, which have to be considered with caution as they only use approximations of the underlying ML model. Therefore, our paper investigates a series of intrinsically interpretable ML models and discusses their suitability for the IS community. More specifically, our focus is on advanced extensions of generalized additive models (GAM) in which predictors are modeled independently in a non-linear way to generate shape functions that can capture arbitrary patterns but remain fully interpretable. In our study, we evaluate the prediction qualities of five GAMs as compared to six traditional ML models and assess their visual outputs for model interpretability. On this basis, we investigate their merits and limitations and derive design implications for further improvements.
Authors with CRIS profile
Patrick Zschech
Assistant Professorship for Intelligent Information Systems
Sven Weinzierl
Lehrstuhl für Digital Industrial Service Systems
Nico Hambauer
Assistant Professorship for Intelligent Information Systems
Sandra Zilker
Lehrstuhl für Digital Industrial Service Systems
Mathias Kraus
Juniorprofessur für Data Analytics
Related research project(s)
How to cite
APA:
Zschech, P., Weinzierl, S., Hambauer, N., Zilker, S., & Kraus, M. (2022). GAM(e) changer or not? An evaluation of interpretable machine learning models based on additive model constraints. In Proceedings of the 30th European Conference on Information Systems (pp. 1-18). Timisoara, RO: AISeL.
MLA:
Zschech, Patrick, et al. "GAM(e) changer or not? An evaluation of interpretable machine learning models based on additive model constraints." Proceedings of the European Conference on Information Systems, Timisoara AISeL, 2022. 1-18.
BibTeX: Download