Selection Rate#
The fraction of a group that receives a positive decision.
Important
✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.
What it is#
The selection rate is the fraction of a group that receives a favorable decision — the share predicted positive, \(P(\hat{Y} = 1)\) for that group. If a lender approves 60% of one group and 40% of another, those are the two selection rates.
What it drives#
Selection rate is the quantity behind demographic parity — parity holds exactly when selection rates are equal across groups. The disparate-impact ratio divides the lowest group’s selection rate by the highest; a ratio below 0.8 (the four-fifths rule) flags potential adverse impact.
Where it’s used#
It is the core number in auditing hiring, lending, and admissions for bias, because it captures who gets the good outcome without needing labels. But equal selection rates say nothing about whether the right people were chosen — that is why it is paired with error-based metrics like recall.
Theme: Fairness & Calibration · All terminology
Hint
Mind map — connected ideas
Fairness parity · Recall · Fair Lending laws · Fairness Guardrails · High-Stakes Domains · Conversion Rate (CR)
Hint
More in Fairness & Calibration
Demographic Parity (Statistical Parity) · Equal Opportunity (Fairness) · Equalized Odds (Fairness) · Fairness Guardrails · Fairness parity · Four-Fifths (80%) Rule · Predictive Parity (Calibration)
See also
Source article Adapted (context, re-expressed) in our own words from: Selection Rate (insightful-data-lab.com).