Decision Threshold Adjuster

A post-processing bias mitigator that optimizes decision thresholds on a trained model's scores so that group outcome or error rates meet the target fairness criterion.

Responsibility. Sets decision thresholds that reduce group disparities in model outcomes.

Also known as: Threshold optimization, Post-hoc adjustment, Post-processing debiasing

Variant of Bias Mitigator abstract

When to choose. Choose (post-processing) to correct a trained model's decisions without retraining, e.g., as an adaptive intervention on production drift; post-hoc correction usually gives weaker fairness-accuracy trade-offs than in-training constraints.