M29.2 CONNECT THE MECHANISM
Choose fairness measurements that match the decision context
Three people check the same model for fairness. One says it's fair, two say it isn't, and all three have done their arithmetic right. Find out how.
LESSON OVERVIEW15 min lesson
Lesson overview
Three people check the same model for fairness. One says it's fair, two say it isn't, and all three have done their arithmetic right. Find out how.
What you’ll explore
- Fairness metrics encode different comparisons among groups and outcomes; label validity, error costs, uncertainty, and incompatible criteria require explicit contextual judgment.
GO TO THE SOURCE
Original explanations, connected to the research.
Equality of Opportunity in Supervised Learning (Hardt, Price & Srebro, 2016)Inherent Trade-Offs in the Fair Determination of Risk Scores (Kleinberg, Mullainathan & Raghavan, 2016)Fair prediction with disparate impact: A study of bias in recidivism prediction instruments (Chouldechova, 2017)Machine Bias (Angwin, Larson, Mattu & Kirchner, ProPublica, May 2016)How We Analyzed the COMPAS Recidivism Algorithm (ProPublica, 2016)Dissecting racial bias in an algorithm used to manage the health of populations (Obermeyer et al., Science, 2019)Suggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.