Advanced · Safety
Equality of opportunity
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. A fairness metric ensuring a model's positive predictions are equally accurate across different sensitive groups.
Technical Definition
A fairness metric ensuring a model's positive predictions are equally accurate across different sensitive groups.
How it works
Equality of opportunity is a fairness criterion that requires a machine learning model to have the same true positive rate for all subgroups defined by a sensitive attribute. In simpler terms, if the model predicts a positive outcome, the likelihood of that prediction being correct should be consistent across different groups. This focuses on fairness for those who should receive the positive outcome.
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.