Papers
arxiv:2111.08749

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

Published on Nov 16, 2021
Authors:
,
,

Abstract

SMACE is a new interpretability method that combines geometric approaches for decision rules with existing model-agnostic methods to provide meaningful feature rankings for complex decision systems using multiple models.

AI-generated summary

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.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2111.08749 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2111.08749 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2111.08749 in a Space README.md to link it from this page.

Collections including this paper 1