Predicting Consumer Default: A Deep Learning Approach

77 Pages Posted: 30 Oct 2019 Last revised: 7 Aug 2020

See all articles by Stefania Albanesi

Stefania Albanesi

University of Pittsburgh

Domonkos F. Vamossy

University of Pittsburgh

Multiple version iconThere are 3 versions of this paper

Date Written: August 29, 2019

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 provides favorable credit risk assessment to young 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 Classification: C45; D14; E27; E44; G21; G24

Suggested Citation

Albanesi, Stefania and Vamossy, Domonkos F., Predicting Consumer Default: A Deep Learning Approach (August 29, 2019). Available at SSRN: https://ssrn.com/abstract=3445152 or http://dx.doi.org/10.2139/ssrn.3445152

Stefania Albanesi

University of Pittsburgh ( email )

135 N Bellefield Ave
Pittsburgh, PA 15260
United States

HOME PAGE: http://https://sites.google.com/site/stefaniaalbanesi/

Domonkos F. Vamossy (Contact Author)

University of Pittsburgh ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
773
Abstract Views
4,155
rank
45,342
PlumX Metrics