Pitfalls to Avoid when Interpreting Machine Learning Models
- Author(s)
- Christoph Molnar, Gunnar König, Julia Herbinger, Timo Freiesleben, Susanne Dandl, Christian A. Scholbeck, Giuseppe Casalicchio, Moritz Grosse-Wentrup, Bernd Bischl
- Abstract
Modern requirements for machine learning (ML) models include both high predictive performance and model interpretability. A growing number of techniques provide model interpretations, but can lead to wrong conclusions if applied incorrectly. We illustrate pitfalls of ML model interpretation such as bad model generalization, dependent features, feature interactions or unjustified causal interpretations. Our paper addresses ML practitioners by raising awareness of pitfalls and pointing out solutions for correct model interpretation, as well as ML researchers by discussing open issues for further research.
- Organisation(s)
- Research Group Neuroinformatics, Research Network Data Science, Vienna Cognitive Science Hub
- External organisation(s)
- Ludwig-Maximilians-Universität München, Universität Wien
- No. of pages
- 10
- DOI
- https://doi.org/10.48550/arXiv.2007.04131
- Publication date
- 07-2020
- Peer reviewed
- Yes
- Austrian Fields of Science 2012
- 102019 Machine learning
- Portal url
- https://ucris.univie.ac.at/portal/en/publications/pitfalls-to-avoid-when-interpreting-machine-learning-models(a1564ed3-b0dc-4a0f-86fc-760b16d85d55).html