Predicting Consumer Default: A Deep Learning Approach

TL;DR

This paper introduces a deep learning model for predicting consumer default that outperforms traditional credit scoring, offers interpretability, and provides broader borrower coverage, aiding policy and systemic risk management.

Contribution

The paper presents a novel deep learning approach that surpasses standard models in accuracy, interpretability, and coverage for consumer default prediction.

Findings

Deep learning model outperforms standard credit scoring models.

Model provides interpretable scores for a wider range of borrowers.

Accurately tracks systemic risk variations.

Abstract

We develop a model to predict consumer default based on deep learning. We show that the model consistently outperforms standard credit scoring models, even though it uses the same data. Our model is interpretable and is able to provide a score to a larger class of borrowers relative to standard credit scoring models while accurately tracking variations in systemic risk. We argue that these properties can provide valuable insights for the design of policies targeted at reducing consumer default and alleviating its burden on borrowers and lenders, as well as macroprudential regulation.