Proceedings of the 2022 International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022)

<Previous Article In Volume
Next Article In Volume>

Optimization of Machine Learning Models for Prediction of Personal Loan Default Rate

Authors
Yanghuai He1, Yuzhe Jian2, Tianyuan Liu3, Huaijin Xue4, *
1International Department of Guangzhou Foreign Language School, Guangzhou, China
2Malvern College, Worcestershire, UK
3Sacred Heart School of Halifax, Halifax, Canada
4School of Mechanical Engineering, Donghua University, Shanghai, China
*Corresponding author. Email: silhouettes-hubery@outlook.com Email: guanghua.ren@gecacademy.cn
Corresponding Author
Huaijin Xue
Available Online 20 December 2022.
DOI
10.2991/978-94-6463-030-5_29How to use a DOI?
Keywords
Machine Learning Models; LightGBM; Random Forest; Credit Default Prediction
Abstract

The credit industry’s continuing expansion depends on the application of modern information technology to lower the risk of credit default. Traditional credit default prediction model research places too much emphasis on the model’s accuracy while ignoring some of its most important characteristics. Simultaneously, the parameter characteristics must be manually removed to reduce the model’s complexity, which lessens the high-dimensional correlation between the analyzed data and lowers the model’s prediction performance. Therefore, this paper constructs two personal credit loan default risk assessment models based on Random Forest (RF) and Light Gradient Boosting Machine (LightGBM), using Accuracy Rate (ACC) and Area Under the ROC Curve (AUC) as performance evaluation metrics. According to empirical studies, the most important determinants affecting loan defaults are ‘debt_loan_ratio’ and ‘known_outstanding_loan’. The AUC of the LightGBM model is above 86%, while RF’s AUC is just about 55%, indicating the better performance for the former one. Overall, these results shed light on the prediction of load default rate, which will be a guideline for further policy implementation.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2022 International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022)
Series
Atlantis Highlights in Intelligent Systems
Publication Date
20 December 2022
ISBN
978-94-6463-030-5
ISSN
2589-4919
DOI
10.2991/978-94-6463-030-5_29How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Yanghuai He
AU  - Yuzhe Jian
AU  - Tianyuan Liu
AU  - Huaijin Xue
PY  - 2022
DA  - 2022/12/20
TI  - Optimization of Machine Learning Models for Prediction of Personal Loan Default Rate
BT  - Proceedings of the 2022 International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022)
PB  - Atlantis Press
SP  - 270
EP  - 282
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-030-5_29
DO  - 10.2991/978-94-6463-030-5_29
ID  - He2022
ER  -