AI engineering glossary · AI ethics law product
What is counterfactual fairness?
Counterfactual fairness: A criterion under which a decision is fair to a person if it would have stayed the same in a hypothetical world where only their protected attribute, and whatever it causally influences, were different. It relies on a causal model of how attributes affect other features.
Counterfactual fairness: an example
A hiring model is counterfactually fair if changing an applicant's gender in a causal model of the world, while keeping their skills, would not change the recommendation.
Related terms
More AI ethics law product terms
- Cross-border data transfer
- CSAT
- Dark patterns
- Data breach notification
- Data controller
- Data Fiduciary
- Data flywheel
- Data minimization
Where you learn it
Counterfactual fairness is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.