Skip to content

Absolute Between-ROC Area (ABROCA) fairness metric

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 review), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

ABROCA is a fairness metric proposed by Gardner et al. (2019) and adopted by several reviewed studies. "This metric measures the absolute value of the area between the baseline group ROC curve ROCb and the comparison group(s) ROCc. The lower the ABROCA value, the less unfair the algorithm." Unlike threshold-dependent metrics such as equalized odds, ABROCA evaluates model discrimination across all thresholds and can be computed directly from prediction modeling results with minimal computational requirement.

Accounts

  • ABROCA: Absolute Between-ROC Area fairness metric: ABROCA is a fairness metric proposed by Gardner et al. (2019) and adopted by several reviewed studies. "This metric measures the absolute value of the area between the baseline group ROC curve ROCb and the comparison group(s) ROCc. The lower the ABROCA value, the less unfair the algorithm." Unlike threshold-dependent metrics such as equalized odds, ABROCA evaluates model discrimination across all thresholds and can be computed directly from prediction modeling results with minimal computational requirement. (Jamiu Adekunle Idowu (2024))

Claims

-

Key Sources

  • Jamiu Adekunle Idowu. (2024). Debiasing Education Algorithms. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-023-00389-4
Page metadata
Field Value
type research-method
id absolute-between-roc-area-abroca-fairness-metric
title Absolute Between-ROC Area (ABROCA) fairness metric
description ABROCA is a fairness metric proposed by Gardner et al.
status review
generated by process:settle-candidates on 2026-10-27
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.