Does RChilli use fairness metrics? If yes, which ones?

Yes. RChilli uses practical and interpretable fairness metrics that are closely tied to hiring outcomes.

Selection rate comparison

This measures whether different candidate groups or controlled profile variations are being shortlisted at similar rates. A large unexplained difference may indicate unfairness.

Score consistency

This checks whether professionally equivalent candidates receive similar scores when only a non-job-related attribute changes. It helps verify that skills and experience are driving the result, not sensitive or proxy signals.

Ranking distribution

This evaluates where candidates appear in ranked results, especially in top-N positions. Since visibility strongly affects review likelihood, ranking fairness is an important part of outcome fairness.

These metrics are used not just to generate numbers, but to confirm that outcomes remain fair, stable, and explainable.

If you need further assistance, feel free to contact the RChilli Support Team by sending an email to support@rchilli.com.