and home insurance premiums • Hiring • School admission • Policing strategies • Criminal sentencing • Differential service offerings • Marketing Yet for moral, legal and societal reasons, must protect from racial, gender, and other discrimination
(e.g. credit history, payment history, rent and house purchase history, number of dependents, driving record, employment record, education, etc) • Protected attribute (e.g. race) • Prediction target (e.g. load defaulting, non-appearance, recidivism) • Learn predictor () or (, ) for • Learn based on training set , , =1.. …can mostly assume population distribution (, , ) is known • What does it mean for to be non-discriminatory?
⊥ Too strict: • What if true correlates with ? • Doesn’t allow perfect prediction = • e.g. give loans exactly to those that won’t default Not weak: • Doesn’t protect from accuracy disparity • e.g. give loans to qualified = 0 people and random = 1 people
provide any additional information about beyond what the truth already tells us on = , = = = , = ′ • The perfect predictor, = , always satisfies equalized odds • Protects against accuracy disparity
Hardt, Eric Price and Nati Srebro • Efficiently and optimally correct discriminatory predictors to satisfy equalizes odds • Interpretation in terms of ROC curves • Incentive structure: • Shifts “cost of uncertainty” from protected group to decision maker • Incentivizes collecting features directly related to target (not via ) • Incentivizes data collection also on minority groups • Inherent limitations of oblivious tests (treating predictor as black box) • Non-identifiability of different scenarios • Why equalized odds and not calibration parity (Northpoint’s “target population errors”)