Fairness-Accuracy Trade-Offs: A Causal Perspective

arXiv:2405.15443v1 Announce Type: new
Abstract: Systems based on machine learning may exhibit discriminatory behavior based on sensitive characteristics such as gender, sex, religion, or race. In light of this, various notions of fairness and methods to quantify discrimination were proposed, leading to the development of numerous approaches for constructing fair predictors. At the same time, imposing fairness constraints may decrease the utility of the decision-maker, highlighting a tension between fairness and utility. This tension is also recognized in legal frameworks, …

abstract accuracy arxiv behavior causal cs.ai cs.lg development discrimination fair fairness gender light machine machine learning perspective race religion sex stat.ml systems trade type