Envy-Free but Still Unfair: Envy-Freeness Up To One Item (EF-1) in Personalized Recommendation
This is an incremental critique for researchers and practitioners in recommendation systems, highlighting limitations of applying traditional fairness metrics.
The paper argues that envy-freeness (EF-1), a fairness concept from economics, is inappropriate for measuring fairness in personalized recommendation systems, as it fails to account for personalization.
Envy-freeness and the relaxation to Envy-freeness up to one item (EF-1) have been used as fairness concepts in the economics, game theory, and social choice literatures since the 1960s, and have recently gained popularity within the recommendation systems communities. In this short position paper we will give an overview of envy-freeness and its use in economics and recommendation systems; and illustrate why envy is not appropriate to measure fairness for use in settings where personalization plays a role.