What is a demographic parity?
A fairness metric that is satisfied if the results of a model's classification are not dependent on a given sensitive attribute.
demographic parity explained in plain English
A fairness metric that is satisfied if the results of a model's classification are not dependent on a given sensitive attribute. For example, if both Lilliputians and Brobdingnagians apply to Glubbdubdrib University, demographic parity is achieved if the percentage of Lilliputians admitted is the same as the percentage of Brobdingnagians admitted, irrespective of whether one group is on average more qualified than the other. Contrast with equalized odds and equality of opportunity, which permit classification results in aggregate to depend on sensitive attributes, but don't permit classification results for certain specified ground truth labels to depend on sensitive attributes. See"Attacking discrimination with smarter machine learning" for a visualization exploring the tradeoffs when optimizing for demographic parity. See Fairness: demographic parity in Machine Learning Crash Course for more information.
Example
Practitioners refer to demographic parity when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- bias
1.
- bias (math) or bias term
An intercept or offset from an origin.
- confirmation bias
The tendency to search for, interpret, favor, and recall information in a way that confirms one's pre-existing beliefs or hypotheses.
- counterfactual fairness
A fairness metric that checks whether a classification model produces the same result for one individual as it does for another individual who is identical to the first, except with respect to one or more sensitive attributes.
- discriminative model
A model that predicts labels from a set of one or more features.
- equality of opportunity
A fairness metric to assess whether a model is predicting the desirable outcome equally well for all values of a sensitive attribute.
- equalized odds
A fairness metric to assess whether a model is predicting outcomes equally well for all values of a sensitive attribute with respect to both the positive class and negative class—not just one class or the other exclusively.
- evaluation
The process of measuring a model's quality or comparing different models against each other.
- fairness metric
A mathematical definition of "fairness" that is measurable.
- generative model
Practically speaking, a model that does either of the following: - Creates (generates) new examples from the training dataset.