Deep neural networks with L1 and L2 regularization for high dimensional corporate credit risk prediction

Yang, M., Lim, M. K. , Qu, Y., Li, X. and Ni, D. (2023) Deep neural networks with L1 and L2 regularization for high dimensional corporate credit risk prediction. Expert Systems with Applications, 213(Part A), 118873. (doi: 10.1016/j.eswa.2022.118873)

Abstract

Accurate credit risk prediction can help companies avoid bankruptcies and make adjustments ahead of time. There is a tendency in corporate credit risk prediction that more and more features are considered in the prediction system. However, this often brings redundant and irrelevant information which greatly impairs the performance of prediction algorithms. Therefore, this study proposes an HDNN algorithm that is an improved deep neural network (DNN) algorithm and can be used for high dimensional prediction of corporate credit risk. We firstly theoretically proved that there was no regularization effect when L1 regularization was added to the batch normalization layer of the DNN, which was a hidden rule in the industrial implementation but never been proved. In addition, we proved that adding L2 constraints on a single L1 regularization can solve the issue. Finally, this study analyzed a case study of credit data with supply chain and network data to show the superiority of the HDNN algorithm in the scenario of a high dimensional dataset.

• Item Type: Articles
• Additional Information: Funding: This work was supported by 2022 Scientific Research Startup Fund of Chongqing Jiaotong University [Grant No. F1210045] and the graduate research and innovation foundation of Chongqing, China [Grant No. CYS21047].
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Lim, Professor Ming
• Authors: Yang, M., Lim, M. K., Qu, Y., Li, X., and Ni, D.
• College/School: College of Social Sciences > Adam Smith Business School > Management
• Journal Name: Expert Systems with Applications
• Publisher: Elsevier
• ISSN: 0957-4174
• ISSN (Online): 1873-6793
• Published Online: 21 September 2022
• Copyright Holders: Copyright © 2022 Elsevier Ltd
• First Published: First published in Expert Systems with Applications 213(Part A): 118873
• Publisher Policy: Reproduced in accordance with the publisher copyright policy