Machine Learning and the Meaning of Equal Treatment

Abstract

Approaches to non-discrimination are generally informed by two principles: striving for equality of treatment, and advancing various notions of equality of outcome. We consider when and why there are trade-offs in machine learning between respecting formalistic interpretations of equal treatment and advancing equality of outcome. Exploring a hypothetical discrimination suit against Facebook, we argue that interpretations of equal treatment which require blindness to difference may constrain how machine learning can be deployed to advance equality of outcome. When machine learning models predict outcomes that are unevenly distributed across racial groups, using those models to advance racial justice will often require deliberately taking race into account. We then explore the normative stakes of this tension. We describe three pragmatic policy options underpinned by distinct interpretations and applications of equal treatment. A status quo approach insists on blindness to difference, permitting the design of machine learning models that compound existing patterns of disadvantage. An industry-led approach would specify a narrow set of domains in which institutions were permitted to use protected characteristics to actively reduce inequalities of outcome. A government-led approach would impose positive duties that require institutions to consider how best to advance equality of outcomes and permit the use of protected characteristics to achieve that goal. We argue that while machine learning offers significant possibilities for advancing racial justice and outcome-based equality, harnessing those possibilities will require a shift in the normative commitments that underpin the interpretation and application of equal treatment in non-discrimination law and the governance of machine learning.