Home / Curated / Evaluation Criteria

Evaluation Criteria

5 Concepts

Defined conditions and loss metrics used to assess model behavior or predictions.

Showing 5 of 5

Concept	Origin	Kind / Branch	Identifier	Evidence / Status
Counterfactual fairness aka CF (counterfactual fairness) A fairness criterion in a specified causal model requiring a predictor's conditional output distribution, given an individual's observed att…	Curated	Evaluation Criteria	`AIMech:CounterfactualFairness`	3 claims 3 sources
Demographic parity aka Statistical parity A group-level prediction criterion requiring the distribution of a decision or prediction to be independent of a specified protected attribu…	Curated	Evaluation Criteria	`AIMech:DemographicParity`	3 claims 3 sources
Equal opportunity in binary classification aka Equal opportunity (true-positive parity), Equality of opportunity (true-positive parity) A binary-classification fairness criterion requiring equal probabilities of a positive prediction across specified protected groups among in…	Curated	Evaluation Criteria	`AIMech:EqualOpportunity`	1 claim 1 source
Equalized odds aka Equalised odds A fairness criterion requiring a predictor's output to be conditionally independent of a specified protected attribute given the target outc…	Curated	Evaluation Criteria	`AIMech:EqualizedOdds`	1 claim 1 source
Lipschitz individual fairness aka Individual fairness (Dwork et al.), Fairness through awareness (Lipschitz criterion) An individual-fairness criterion requiring the distance between the output distributions assigned by a randomized classifier to any two indi…	Curated	Evaluation Criteria	`AIMech:LipschitzIndividualFairness`	1 claim 1 source