Multi-level credit risk prediction model based on deep learning

Ye Pang; Chunling Chen

doi:10.1117/12.2641864

19 October 2022 Multi-level credit risk prediction model based on deep learning

Ye Pang, Chunling Chen

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 122945L (2022) https://doi.org/10.1117/12.2641864
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

In order to promote the application of deep neural network technology in the field of bank credit risk prediction and improve the prediction accuracy and efficiency of deep neural network in the field of bank credit risk prediction, a bank credit risk prediction model based on multi-level deep neural network is designed. By taking the weighted sum data of the customer characteristics obtained by the analytic hierarchy process as the input of the model, the coarse-grained screening is carried out by the h-net of the model. The customers whose credit evaluation is higher than the threshold are further screened by the L-net of the model, and finally the customer's credit score is output. The depth of credit risk can be predicted by neural network. The experiment on the real loan data of a commercial bank shows that the model has high prediction accuracy and efficiency.

Citation Download Citation

Ye Pang and Chunling Chen "Multi-level credit risk prediction model based on deep learning", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 122945L (19 October 2022); https://doi.org/10.1117/12.2641864

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available