DeepAI
Log In Sign Up

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

02/15/2022
by   YinYin Yu, et al.
0

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.

READ FULL TEXT
07/10/2020

Algorithmic Fairness in Education

Data-driven predictive models are increasingly used in education to supp...
09/20/2022

Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation

The goal of this work is to help mitigate the already existing gender wa...
02/23/2018

An Algorithmic Framework to Control Bias in Bandit-based Personalization

Personalization is pervasive in the online space as it leads to higher e...
12/05/2022

Certifying Fairness of Probabilistic Circuits

With the increased use of machine learning systems for decision making, ...
04/12/2021

Towards Algorithmic Transparency: A Diversity Perspective

As the role of algorithmic systems and processes increases in society, s...
12/18/2020

Affirmative Algorithms: The Legal Grounds for Fairness as Awareness

While there has been a flurry of research in algorithmic fairness, what ...
06/01/2022

Sex and Gender in the Computer Graphics Research Literature

We survey the treatment of sex and gender in the Computer Graphics resea...