Existing tools for explaining complex models and systems are associational rather than causal and do not provide mechanistic understanding. Motivated by the concept of genetic heritability in twin studies, this talk will introduce a new notion called …
We propose a counterfactual notion of explainability.
This is an invited commentary for Statistical Science on the causal inference data competition in ACIC 2016.
We link Friedman's partial dependence plot with Pearl's backdoor adjustment formula. We discuss situations when possible causal interpretations can be made for black-box machine learning models.