Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Exploration

arXiv:2404.05270v1 Announce Type: cross
Abstract: Algorithmic Recourse aims to provide actionable explanations, or recourse plans, to overturn potentially unfavourable decisions taken by automated machine learning models. In this paper, we propose an interaction paradigm based on a guided interaction pattern aimed at both eliciting the users' preferences and heading them toward effective recourse interventions. In a fictional task of money lending, we compare this approach with an exploratory interaction pattern based on a combination of alternative plans and the possibility …

abstract arxiv automated automated machine learning cs.cy cs.hc cs.lg decisions exploration interactive machine machine learning machine learning models paper paradigm type