Working Paper: CEPR ID: DP13914
Authors: Stefania Albanesi; Domonkos Vamossy
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.
Keywords: consumer default; credit scores; deep learning; macroprudential policy
JEL Codes: C45; D1; E27; E44; G21; G24
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| deep learning model (C45) | better predictions of consumer default (G51) |
| deep learning model (C45) | outperform standard credit scoring models (C52) |
| deep learning model (C45) | track variations in systemic risk (E44) |
| standard credit scoring models (C52) | limitations in predicting default (G33) |