The Measure and Mismeasure of Fairness

Understand

The field of fair machine learning aims to ensure that decisions guided by algorithms are equitable.

• Over the last decade, several formal, mathematical definitions of fairness have gained prominence.
• Here we first assemble and categorize these definitions into two broad families: (1) those that constrain the effects of decisions on disparities; and (2) those that constrain the effects of legally protected characteristics, like race and gender, on decisions.
• We then show, analytically and empirically, that both families of definitions typically result in strongly Pareto dominated decision policies.