On the relation between accuracy and fairness in binary classification
This work addresses methodological issues in fairness evaluation for binary classification, offering incremental improvements for researchers and practitioners.
The study revisits the accuracy-fairness tradeoff in binary classification, arguing that comparisons of non-discriminatory classifiers must account for varying positive prediction rates to avoid misleading conclusions, and provides methodological recommendations with theoretical and empirical analysis.
Our study revisits the problem of accuracy-fairness tradeoff in binary classification. We argue that comparison of non-discriminatory classifiers needs to account for different rates of positive predictions, otherwise conclusions about performance may be misleading, because accuracy and discrimination of naive baselines on the same dataset vary with different rates of positive predictions. We provide methodological recommendations for sound comparison of non-discriminatory classifiers, and present a brief theoretical and empirical analysis of tradeoffs between accuracy and non-discrimination.