Intermediate · Safety
Demographic parity
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. A fairness metric ensuring prediction rates are the same across different demographic groups.
Technical Definition
A fairness metric ensuring prediction rates are the same across different demographic groups.
How it works
Demographic parity is a fairness criterion that requires the model's prediction rates to be equal across different protected groups, regardless of their actual qualifications or underlying distributions. For instance, if a loan application model exhibits demographic parity, the approval rate would be the same for all racial groups. It's a strict form of fairness that may sometimes conflict with accuracy.
Related Concepts
- Fairness — The principle that AI systems should treat individuals and groups equitably.
- Bias (ethics/fairness) — Unfair prejudice or favoritism towards certain groups or things, which can influence data, system design, and user interactions.
- Responsible AI (RAI) — A holistic framework encompassing the ethical, legal, and societal implications of AI, promoting trustworthy and beneficial systems.