Research on credit risk assessment based on machine learning

Tingting Liu; Dongxian Huang

doi:10.1117/12.2661107

16 December 2022 Research on credit risk assessment based on machine learning

Tingting Liu, Dongxian Huang

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 125005R (2022) https://doi.org/10.1117/12.2661107
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

Due to the large differences in Internet technology and data application among financial institutions in China, some city commercial banks and rural commercial banks are still in the initial stage of exploration in the technical application of internet credit loan business, and their default risk management capabilities are weak and difficult to achieve. Effectively identify the applicant's risk of default. Aiming at the problem of credit risk, on the basis of studying the methods of prevention and control of pre-loan risk, this paper uses various methods such as coding and variables to process credit data. The random forest method is integrated to select variables, and the weighted logistic regression method is used to construct a pre-loan risk early warning model, which can perceive credit risks in advance and give early warnings. On the basis of studying random forest algorithm and parameter optimization method, a post-loan risk early warning model based on random forest algorithm is designed; and the model parameters are optimized to make the risk early warning model have high accuracy. Subsequently, this paper uses about 900,000 credit data of Lending Club in 2016 and 2017 as samples, and divides user data sets that are easier to classify based on the user level identified by Lending Club, and then uses the machine learning model to evaluate and verify the results. The effectiveness of selected models in credit risk assessment scenarios.

Citation Download Citation

Tingting Liu and Dongxian Huang "Research on credit risk assessment based on machine learning", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 125005R (16 December 2022); https://doi.org/10.1117/12.2661107

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