Author(s)  
Stefania Albanesi, Domonkos F. Vamossy

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.

Publication Type  
Working Paper
File Description  
First version, August 29, 2019
JEL Codes  
D14: Personal Finance
E44: Financial Markets and the Macroeconomy
G21: Banks; Depository Institutions; Micro Finance Institutions; Mortgages
Keywords  
consumer default
credit scores
deep learning
macroprudential policy