Choosing an algorithmic fairness metric for an online marketplace: Detecting and quantifying algorithmic bias on LinkedIn

In this paper, we derive an algorithmic fairness metric for the recommendation algorithms that power LinkedIn from the fairness notion of equal opportunity for equally qualified candidates. We borrow from the economic literature on discrimination to arrive at a test for detecting algorithmic discrimination, which we then use to audit two algorithms from LinkedIn with respect to gender bias. Moreover, we introduce a framework for distinguishing algorithmic bias from human bias, both of which can potentially exist on a two-sided platform.