Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Exploration
This addresses the challenge of user-centered algorithmic recourse for individuals affected by automated decisions, but it is an incremental exploration focusing on interaction patterns.
The paper tackles the problem of providing actionable explanations (recourse plans) for automated ML decisions by comparing guided vs. exploratory interaction paradigms in a money lending task, finding that guided interactions improve efficiency but reduce freedom, while exploratory ones are perceived as less efficient and attractive.
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 of freely changing the configurations by the users themselves. Our results suggest that users may recognize that the guided interaction paradigm improves efficiency. However, they also feel less freedom to experiment with "what-if" scenarios. Nevertheless, the time spent on the purely exploratory interface tends to be perceived as a lack of efficiency, which reduces attractiveness, perspicuity, and dependability. Conversely, for the guided interface, more time on the interface seems to increase its attractiveness, perspicuity, and dependability while not impacting the perceived efficiency. That might suggest that this type of interfaces should combine these two approaches by trying to support exploratory behavior while gently pushing toward a guided effective solution.