“…While being intuitive and simple to implement, k-nearest neighbor regression is well-understood from the point of view of theory as well, see e.g. [2], [3], [13], and the references therein for an overview of the most important theoretical results. These theoretical results are also justified by empirical studies: for example, in their recent paper, Stensbo-Smidt et al found that nearest neighbor regression outperforms model-based prediction of star formation rates [30], while Hu et al showed that a model based on k-nearest neighbor regression is able to estimate the capacity of lithium-ion batteries [19].…”