2000 character limit reached
Causality-based Explanation of Classification Outcomes (2003.06868v2)
Published 15 Mar 2020 in cs.LG, cs.AI, cs.DB, and stat.ML
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.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.