When Are Two Lists Better than One?: Benefits and Harms in Joint Decision-making

arXiv:2308.11721v3 Announce Type: replace
Abstract: Historically, much of machine learning research has focused on the performance of the algorithm alone, but recently more attention has been focused on optimizing joint human-algorithm performance. Here, we analyze a specific type of human-algorithm collaboration where the algorithm has access to a set of $n$ items, and presents a subset of size $k$ to the human, who selects a final item from among those $k$. This scenario could model content recommendation, route planning, or …

abstract algorithm analyze arxiv attention benefits collaboration cs.cy cs.hc cs.lg decision human lists machine machine learning making performance research the algorithm type