Fair Sequential Selection Using Supervised Learning Models

We consider a selection problem where sequentially arrived applicants apply for a limited number of positions/jobs. At each time step, a decision maker accepts or rejects the given applicant using a pre-trained supervised learning model until all the vacant positions are filled. In this paper, we discuss whether the fairness notions (e.g., equal opportunity, statistical parity, etc.) that are commonly used in classification problems are suitable for the sequential selection problems. In particular, we show that even with a pre-trained model that satisfies the common fairness notions, the selection outcomes may still be biased against certain demographic groups. This observation implies that the fairness notions used in classification problems are not suitable for a selection problem where the applicants compete for a limited number of positions. We introduce a new fairness notion, "Equal Selection (ES)," suitable for sequential selection problems and propose a post-processing approach to satisfy the ES fairness notion. We also consider a setting where the applicants have privacy concerns, and the decision maker only has access to the noisy version of sensitive attributes. In this setting, we can show that the perfect ES fairness can still be attained under certain conditions. 1. Pre-processing: remove pre-existing biases by modifying the training datasets before the training process [20, 21]; 2. In-processing: impose certain fairness constraint during the training process, e.g., solve a constrained optimization problem or add a regularizer to the objective function [22, 23] ; 3. Post-processing: mitigate biases by changing the output of an existing algorithm [10, 24] . Among fairness constraints, statistical parity, equalized odds, and equal opportunity have gained an increasing attention in supervised learning. Dwork et al. [25] studies the relation between individual fairness and statistical parity. They identify conditions under which individual fairness implies