Question

A company builds an ML model that screens job applicants and recommends candidates for interviews. The compliance team wants to verify that the model recommends candidates at similar rates across gender groups, regardless of any differences in the applicant pool. Which fairness concept should the team measure to confirm this specific requirement?

Accepted Answer

Demographic parity — the proportion of positive outcomes is similar across groups

Answer

Model robustness — the model resists adversarial or noisy inputs

Answer

Explainability — each recommendation includes a feature-attribution rationale

Answer

Perplexity — the fluency of the model's generated output