Skip to content

Explainer: What Is a Precision-Recall Curve (and When to Prefer It Over ROC/AUC)? #92

Description

@yakew7

Add explainers/precision-recall-curve.md.

Companion to the new ROC Curve and AUC explainer. Explain what a PR curve shows, how average precision differs from AUC, and why PR curves are the more honest picture under heavy class imbalance — exactly the regime most fairness audits live in (rare positives, skewed base rates). Tie the fairness angle to why a high ROC-AUC can look reassuring while precision collapses for a minority subgroup.

Suggested structure (match roc-curve-auc.md / false-positives-vs-false-negatives.md): one-sentence definition → why it matters for fairness → core concept → concrete example tied to a repo audit → runnable detection code → limitations → related concepts/projects/further reading.

Related: roc-curve-auc, false-positives-vs-false-negatives, predictive-parity.

See CONTRIBUTING.md: add explainers/<slug>.md plus a one-line entry in assets/explainers-data.json; the build script generates the page.

Freeze-safe: explainers are fully open for contribution during the paper freeze. If you quote any Fair Code benchmark result, use the frozen numbers in paper/results-frozen/ (never re-run your own) — see CLAUDE.md.

Metadata

Metadata

Assignees

No one assigned

    Labels

    documentationImprovements or additions to documentationhelp wantedExtra attention is needed

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions