Index Ai Academy
Glossary · Phase 11 · Professional practice

Equal opportunity

A fairness definition: among the people who deserve a yes, each group gets one equally often. It compares true positive rates.

Try it now

The audit table from the cell above. Lit: where B is treated worse on errors.

Learn it properly

Measuring fairness · Break a model's results down by group: selection rate, true and false positive rates and precision, why they can't all be equal, what each fix costs, and when a group is too small to judge. About 40 minutes.

Other terms from the same lesson

  • demographic parity: A fairness definition: each group is selected at the same rate, whatever their true outcomes.
  • equalized odds: A fairness definition: both the true positive rate and the false positive rate are equal between groups.
  • four-fifths rule: A screening rule from United States employment guidance: a group selected at less than 80% of the highest group's rate is a sign of adverse impact.
  • predictive parity: A fairness definition: a yes means the same thing in each group. It compares precision.
  • selection rate: The share of a group that a model selects, such as the share of applicants approved.
Keep learning

More in plain English.

1286 terms in the glossary, each with the lesson that teaches it.

1286 terms

The glossary

Every word you'll meet in AI and machine learning, explained in everyday language.

Phase 11 · lesson 40 min

Measuring fairness

Break a model's results down by group: selection rate, true and false positive rates and precision, why they can't all be equal, what each fix costs, and when a group is too small to judge.

Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write