SMACE: A New Method for the Interpretability of Composite Decision Systems

Gianluigi Lopardo, Damien Garreau, Frédéric Precioso, Greger Ottosson

ECML-PKDD 2022 pp. 325-339

doi:10.1007/978-3-031-26387-3_20 /ecmlpkdd/2022/lopardo2022ecmlpkdd-smace/

Abstract

Interpretability is a pressing issue for decision systems. Many post hoc methods have been proposed to explain the predictions of a single machine learning model. However, business processes and decision systems are rarely centered around a unique model. These systems combine multiple models that produce key predictions, and then apply decision rules to generate the final decision. To explain such decisions, we propose the Semi-Model-Agnostic Contextual Explainer (SMACE), a new interpretability method that combines a geometric approach for decision rules with existing interpretability methods for machine learning models to generate an intuitive feature ranking tailored to the end user. We show that established model-agnostic approaches produce poor results on tabular data in this setting, in particular giving the same importance to several features, whereas SMACE can rank them in a meaningful way.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Lopardo et al. "SMACE: A New Method for the Interpretability of Composite Decision Systems." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022. doi:10.1007/978-3-031-26387-3_20

Markdown

[Lopardo et al. "SMACE: A New Method for the Interpretability of Composite Decision Systems." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022.](https://mlanthology.org/ecmlpkdd/2022/lopardo2022ecmlpkdd-smace/) doi:10.1007/978-3-031-26387-3_20

BibTeX

@inproceedings{lopardo2022ecmlpkdd-smace,
  title     = {{SMACE: A New Method for the Interpretability of Composite Decision Systems}},
  author    = {Lopardo, Gianluigi and Garreau, Damien and Precioso, Frédéric and Ottosson, Greger},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2022},
  pages     = {325-339},
  doi       = {10.1007/978-3-031-26387-3_20},
  url       = {https://mlanthology.org/ecmlpkdd/2022/lopardo2022ecmlpkdd-smace/}
}