Fair and Interpretable Algorithmic Hiring using Evolutionary Many Objective Optimization

Abstract

Hiring is a high-stakes decision-making process that balances the joint objectives of being fair and accurately selecting the top candidates. The industry standard method employs subject-matter experts to manually generate hiring algorithms; however, this method is resource intensive and finds sub-optimal solutions. Despite the recognized need for algorithmic hiring solutions to address these limitations, no reported method currently supports optimizing predictive objectives while complying to legal fairness standards. We present the novel application of Evolutionary Many-Objective Optimization (EMOO) methods to create the first fair, interpretable, and legally compliant algorithmic hiring approach. Using a proposed novel application of Dirichlet-based genetic operators for improved search, we compare state-of-the-art EMOO models (NSGA-III, SPEA2-SDE, bi-goal evolution) to expert solutions, verifying our results across three real world datasets across diverse organizational positions. Experimental results demonstrate the proposed EMOO models outperform human experts, consistently generate fairer hiring algorithms, and can provide additional lift when removing constraints required for human analysis.