Equalized Odds Testing

From The Foundation for Best Practices in Machine Learning

Equalized Odds Testing

Control

If applicable, test Model(s) for equalized odds. Evaluate whether Model(s) predict a Positive & Negative Outcome for (Sub)population members that are actually in the positive & negative class respectively at the same rates across (Sub)populations.


Aim

To (a) ensure that (i) protected (Sub)populations who should receive the Positive Outcome are receiving the Positive Outcome as often as other (Sub)populations, and (ii) protected (Sub)populations who should not receive the Positive Outcome are not receiving the Positive Outcome as often as other (Sub)populations; and (b) highlight associated risks that might occur in the Product Lifecycle.


Additional Information