Causality-based Explanation of Classification Outcomes
Leopoldo Bertossi, Jordan Li, Maximilian Schleich, Dan Mircea Suciu, Zografoula Vagena · 2020
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.