Improving the Predictive Performances of $k$ Nearest Neighbors Learning by Efficient Variable Selection

TL;DR

This paper demonstrates that using an efficient forward variable selection method significantly enhances the predictive accuracy of k-nearest neighbors models on both simulated and real-world datasets.

Contribution

It introduces a novel forward variable selection approach that markedly improves k-NN performance, outperforming traditional models with stepwise selection.

Findings

Enhanced predictive accuracy of k-NN with variable selection

Outperformance over regression models in experiments

Effective on both simulated and real-world data

Abstract

This paper computationally demonstrates a sharp improvement in predictive performance for $k$ nearest neighbors thanks to an efficient forward selection of the predictor variables. We show both simulated and real-world data that this novel repeatedly approaches outperformance regression models under stepwise selection