Predicting Mortgage Default with Machine Learning: AutoML, Class Imbalance, and Leakage Control

TL;DR

This paper evaluates machine learning methods for mortgage default prediction, emphasizing leakage control and class imbalance handling, and finds AutoML approaches like AutoGluon perform best on real-world data.

Contribution

It introduces leakage-aware feature selection, strict temporal data splitting, and class imbalance techniques, providing a comprehensive comparison of models including AutoML for mortgage default prediction.

Findings

AutoGluon achieves the highest AUROC among evaluated models.

Performance remains stable across different class imbalance ratios.

Leakage control and temporal splitting improve evaluation reliability.

Abstract

Mortgage default prediction is a core task in financial risk management, and machine learning models are increasingly used to estimate default probabilities and provide interpretable signals for downstream decisions. In real-world mortgage datasets, however, three factors frequently undermine evaluation validity and deployment reliability: ambiguity in default labeling, severe class imbalance, and information leakage arising from temporal structure and post-event variables. We compare multiple machine learning approaches for mortgage default prediction using a real-world loan-level dataset, with emphasis on leakage control and imbalance handling. We employ leakage-aware feature selection, a strict temporal split that constrains both origination and reporting periods, and controlled downsampling of the majority class. Across multiple positive-to-negative ratios, performance remains stable, and an AutoML approach (AutoGluon) achieves the strongest AUROC among the models evaluated. An extended and pedagogical version of this work will appear as a book chapter.