Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search
Recently, policymakers, regulators, and advocates have raised awareness about the ethical, policy, and legal challenges posed by machine learning and data-driven systems. In particular, they have expressed concerns about their potentially discriminatory impact, for example, due to inadvertent encoding of bias into automated decisions. For search and recommendation systems, our goal is to understand whether there is bias in the underlying machine learning models, and devise techniques to mitigate the bias. This paper presents a framework for quantifying and mitigating algorithmic bias in mechanisms designed for ranking individuals, typically used as part of web-scale search and recommendation systems. We first propose complementary measures to quantify bias with respect to protected attributes such as gender and age. We then present algorithms for computing fairness-aware re-ranking of results towards mitigating algorithmic bias. Our algorithms seek to achieve a desired distribution of top ranked results with respect to one or more protected attributes. We show that such a framework can be utilized to achieve fairness criteria such as equality of opportunity and demographic parity depending on the choice of the desired distribution. We evaluate the proposed algorithms via extensive simulations and study the effect of fairness-aware ranking on both bias and utility measures. We finally present the online A/B testing results from applying our framework towards representative ranking in LinkedIn Talent Search. Our approach resulted in tremendous improvement in the fairness metrics without affecting the business metrics, which paved the way for deployment to 100 Recruiter users worldwide. Ours is the first large-scale deployed framework for ensuring fairness in the hiring domain, with the potential positive impact for more than 575M LinkedIn members.
READ FULL TEXT