Default risk prediction and feature extraction using a penalized deep neural network

Cunjie Lin; Nan Qiao; Wenli Zhang; Yang Li; Shuangge Ma

doi:10.1007/s11222-022-10140-z

Default risk prediction and feature extraction using a penalized deep neural network

Stat Comput. 2022;32(5):76. doi: 10.1007/s11222-022-10140-z. Epub 2022 Sep 15.

Authors

Cunjie Lin^{1

2}, Nan Qiao², Wenli Zhang², Yang Li^{1

2

3}, Shuangge Ma^{2

4}

Affiliations

¹ Center for Applied Statistics, Renmin University of China, Beijing, 100872 China.
² School of Statistics, Renmin University of China, Beijing, 100872 China.
³ Statistical Consulting Center, Renmin University of China, Beijing, 100872 China.
⁴ Department of Biostatistics, Yale University, New Haven, CT 06511 USA.

Abstract

Online peer-to-peer lending platforms provide loans directly from lenders to borrowers without passing through traditional financial institutions. For lenders on these platforms to avoid loss, it is crucial that they accurately assess default risk so that they can make appropriate decisions. In this study, we develop a penalized deep learning model to predict default risk based on survival data. As opposed to simply predicting whether default will occur, we focus on predicting the probability of default over time. Moreover, by adding an additional one-to-one layer in the neural network, we achieve feature selection and estimation simultaneously by incorporating an $L_{1}$ -penalty into the objective function. The minibatch gradient descent algorithm makes it possible to handle massive data. An analysis of a real-world loan data and simulations demonstrate the model's competitive practical performance, which suggests favorable potential applications in peer-to-peer lending platforms.

Keywords: Feature extraction; Loan data; Neural network; Risk prediction; Survival analysis.

© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022, Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.