Causality-based Explanation of Classification Outcomes
Machine Learning
2020-05-26 v2 Artificial Intelligence
Databases
Machine Learning
Abstract
We propose a simple definition of an explanation for the outcome of a classifier based on concepts from causality. We compare it with previously proposed notions of explanation, and study their complexity. We conduct an experimental evaluation with two real datasets from the financial domain.
Keywords
Cite
@article{arxiv.2003.06868,
title = {Causality-based Explanation of Classification Outcomes},
author = {Leopoldo Bertossi and Jordan Li and Maximilian Schleich and Dan Suciu and Zografoula Vagena},
journal= {arXiv preprint arXiv:2003.06868},
year = {2020}
}
Comments
16 pages, 6 figures, 1 table