Predicting mortgage early delinquency with machine learning methods

•This paper investigates the performance of thirteen methods for modelling and predicting mortgage early delinquency probabilities.•Heterogenous ensemble methods lead other methods in the training, out-of-sample, and out-of-time datasets in terms of risk classification.•Various predictive accuracy performance measures yield different rankings among the thirteen methods and no method consistently dominates in this performance dimension in the training, out-of-sample, and out-of-time data.