Research on Personal Credit Risk Assessment Model Based on Proportional Bootstrap and Stacking
DOI: 10.23977/ferm.2024.070410 | Downloads: 3 | Views: 63
Author(s)
Shenghao Deng 1, Shengran Fu 2
Affiliation(s)
1 School of Mathematics and Systems Science, Guangdong Polytechnic Normal University, Guangzhou, 510450, China
2 School of Finance, Jilin University of Finance and Economics, Changchun, 130117, China
Corresponding Author
Shenghao DengABSTRACT
The personal credit business is an integral component of the modern financial framework. The automation of personal credit evaluation and approval processes, facilitated by machine learning technologies, has the potential to significantly enhance the operational efficiency of financial services. Nevertheless, a critical challenge that must be confronted is the imbalance in sample proportions between defaulting and non-defaulting client categories. In light of this issue, the present study introduces a Bagging algorithm that incorporates proportional sampling and employs the stacking approach to reintegrate the Bagging model, aiming to augment the predictive capabilities of the model. This methodology serves a dual purpose: it mitigates the overfitting induced by imbalanced samples through strategic resampling, while also enhancing the accuracy and robustness of the prediction model via the application of model fusion techniques. Empirical data analysis corroborates that the proposed method outperforms several classical prediction models in terms of Area Under the Curve (AUC) scores and demonstrates superior robustness. Furthermore, since the base model within the Bagging algorithm is agnostic to the specific model, it allows for the fitting of flexible and varied connection functions. When the base model utilizes interpretable machine learning methods, it additionally enables the extraction of the significance of each credit feature in relation to the probability of default.
KEYWORDS
Credit Risk, Imbalanced Sample, Bagging, StackingCITE THIS PAPER
Shenghao Deng, Shengran Fu, Research on Personal Credit Risk Assessment Model Based on Proportional Bootstrap and Stacking. Financial Engineering and Risk Management (2024) Vol. 7: 77-84. DOI: http://dx.doi.org/10.23977/ferm.2024.070410.
REFERENCES
[1] Zhou Yuping, Chen Guanyu. Research on the Individual Credit Evaluation Based on the Machine Learning Method [J]. Financial Theory & Practice, 2019(12): 1-8.
[2] Tao Zhourong. Research on Combined Model of Personal Credit Risk Assessment [D]. East China Normal University, 2023.
[3] BAI Pengfei, AN Qi, Nicolaas Fransde ROOIJ, et al. Internet Credit Personal Credit Assessing Method Based on Multi-Model Ensemble [J]. Journal of South China Normal University (Natural Science Edition), 2017, 49(06): 119-123.
[4] Liao Wenxiong, Zeng Bi, Liang Tiankai, et al. Personal Credit Assessment Method for High-Dimensional Data [J]. Computer Engineering and Applications, 2020, 56(04): 219-224.
[5] Zhang Liying, Yang Ruojin. The Application Research of Huoseholds' Loan Default Prediction Model Based on Machine Learning [J]. Financial Regulation Research, 2022, (06): 46-59.
[6] Wang Yufei. Research on Credit Default Prediction Based On Stacking [D]. Lanzhou University, 2024.
[7] Cao Jie, Shao Xiaoxiao. Analysis of Personal Credit Evaluation Method Based on Information Gain and Bagging Integration Learning Algorithm [J]. Mathematics in Practice and Theory, 2016, 46(08): 90-98.
[8] Wang Ruijie, Bao Tengfei, Li Yangtao, Song Baogang, Xiang Zhenyang. Combined prediction model of dam deformation based on multi-factor fusion and Stacking ensemble learning [J]. Journal of Hydraulic Engineering, 2023, 54(04): 497-506.
Downloads: | 21326 |
---|---|
Visits: | 398727 |
Sponsors, Associates, and Links
-
Information Systems and Economics
-
Accounting, Auditing and Finance
-
Industrial Engineering and Innovation Management
-
Tourism Management and Technology Economy
-
Journal of Computational and Financial Econometrics
-
Accounting and Corporate Management
-
Social Security and Administration Management
-
Population, Resources & Environmental Economics
-
Statistics & Quantitative Economics
-
Agricultural & Forestry Economics and Management
-
Social Medicine and Health Management
-
Land Resource Management
-
Information, Library and Archival Science
-
Journal of Human Resource Development
-
Manufacturing and Service Operations Management
-
Operational Research and Cybernetics