Utility-Maximizing Binary Prediction via the Nearest Neighbor Method and Its Application to Credit Scoring

We propose nonparametric <i>k</i>-nearest neighbor prediction rules under the framework of utility-maximizing binary prediction with possibly many predictors. One of these prediction rules, with an attempt to “break” the curse of dimensionality, is constructed based on the predictors selected by variable selection methods. We establish that allowing for the data-dependent selection of parameter <i>k</i>, these prediction rules are utility consistent under regularity assumptions. Such utility consistency is confirmed by the simulation results. We illustrate these prediction rules with an application to credit scoring in peer-to-peer lending and find that common predictors of the business cycle yield limited improvement in profitability.