Learning Social Fairness Preferences from Non-Expert Stakeholder Opinions in Kidney Placement

arXiv:2404.03800v1 Announce Type: new
Abstract: Modern kidney placement incorporates several intelligent recommendation systems which exhibit social discrimination due to biases inherited from training data. Although initial attempts were made in the literature to study algorithmic fairness in kidney placement, these methods replace true outcomes with surgeons' decisions due to the long delays involved in recording such outcomes reliably. However, the replacement of true outcomes with surgeons' decisions disregards expert stakeholders' biases as well as social opinions of other stakeholders who …

abstract algorithmic fairness arxiv biases cs.hc cs.lg data decisions discrimination expert fairness intelligent literature modern opinions placement recommendation recommendation systems social stakeholder study systems training training data true type