Claire Lazar Reich

Suhas Vijaykumar, Claire Lazar Reich

Modern algorithms for binary classification rely on an intermediate regression problem for computational tractability. In this paper, we establish a geometric distinction between classification and regression that allows risk in these two settings to be more precisely related. In particular, we note that classification risk depends only on the direction of the regressor, and we take advantage of this scale invariance to improve existing guarantees for how classification risk is bounded by the risk in the intermediate regression problem. Building on these guarantees, our analysis makes it possible to compare algorithms more accurately against each other and suggests viewing classification as unique from regression rather than a byproduct of it. While regression aims to converge toward the conditional expectation function in location, we propose that classification should instead aim to recover its direction.

Claire Lazar Reich

Critical decisions in hiring, college admissions, and credit lending are guided by predictions made in the presence of uncertainty. While uncertainty imparts errors across all demographic groups, this paper shows that the types of errors vary systematically: Groups with higher average outcomes are typically assigned higher false positive rates, while those with lower average outcomes are assigned higher false negative rates. We characterize the conditions that give rise to this disparate impact and explain why the intuitive remedy to omit demographic variables from datasets does not correct it. Instead of data omission, this paper examines how data acquisition can broaden access to opportunity. The strategy, which we call "Affirmative Information," could stand as an alternative to Affirmative Action.

Claire Lazar Reich, Suhas Vijaykumar

Decision makers increasingly rely on algorithmic risk scores to determine access to binary treatments including bail, loans, and medical interventions. In these settings, we reconcile two fairness criteria that were previously shown to be in conflict: calibration and error rate equality. In particular, we derive necessary and sufficient conditions for the existence of calibrated scores that yield classifications achieving equal error rates at any given group-blind threshold. We then present an algorithm that searches for the most accurate score subject to both calibration and minimal error rate disparity. Applied to the COMPAS criminal risk assessment tool, we show that our method can eliminate error disparities while maintaining calibration. In a separate application to credit lending, we compare our procedure to the omission of sensitive features and show that it raises both profit and the probability that creditworthy individuals receive loans.