Avoiding Discrimination through Causal Reasoning

Understand

Recent work on fairness in machine learning has focused on various statistical discrimination criteria and how they trade off.

• Most of these criteria are observational: They depend only on the joint distribution of predictor, protected attribute, features, and outcome.
• While convenient to work with, observational criteria have severe inherent limitations that prevent them from resolving matters of fairness conclusively.
• Going beyond observational criteria, we frame the problem of discrimination based on protected attributes in the language of causal reasoning.