Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on Default Rate of Financing Projects of Online Lending Platform Based on XGBoost Model

Download as PDF

DOI: 10.23977/ferm.2021.040104 | Downloads: 16 | Views: 762

Author(s)

Xigan Sun 1

Affiliation(s)

1 School of Aeronautical Science and Engineering, Beihang University, Beijing 100000, China

Corresponding Author

Xigan Sun

ABSTRACT

In recent years, with the rapid development of the online credit industry and the wide application of big data technology, using an integrated learning model to evaluate loan risk quickly and accurately has been a concern by academics and practitioners. In order to predict the default rate of the financing projects of the online loan platform with high accuracy and efficiency, this paper adopts the XGBoost model based on the importance of certain features to process loan application data of an online loan platform and establishes the default rate prediction model of online loan projects. Ten years' loan application data of American online lending platforms were selected to verify the model, and the prediction results were compared with those of Random Forest (RF) and LightGBM. The results show that the XGBoost model based on the optimization derivation and the second-order Taylor expansion has higher accuracy in the evaluation.

KEYWORDS

Default Rate, Financing Projects, Online Lending, XGBoost Model

CITE THIS PAPER

Xigan Sun, Research on Default Rate of Financing Projects of Online Lending Platform Based on XGBoost Model. Financial Engineering and Risk Management (2021) 4: 60-68. DOI: http://dx.doi.org/10.23977/ferm.2021.040104

REFERENCES

[1] CHEN Qiu-hua, YANG Hui-rong, CUI Heng-jian. Personal Credit Scoring Model and Statistical Learning after Variable Selection [J]. Journal of Applied Statistics and Management, 2020, 39 (02): 368-380.
[2] LENG Aolin, XING Guangyuan, FAN Weiguo. Credit Risk Transfer in SME Loan Guarantee Networks [J]. Journal of Systems Science & Complexity, 2017, 30 (05): 1084-1096.
[3] LIU Xuefeng, ZHANG Wei, XIONG Xiong, SHEN Dehua, ZHANG Yongjie. Credit Rationing and the Simulation of Bank-Small and Medium Sized Firm Artificial Credit Market [J]. Journal of Systems Science & Complexity, 2016, 29(04): 991-1017.
[4] PRAGER David, ZHANG Qing. Valuation of Stock Loans under a Markov Chain Model [J]. Journal of Systems Science & Complexity, 2016, 29 (01): 171-186.
[5] Xiao Wenbing, Fei Qi, Wan Hu. Credit scoring models and credit-risk evaluation based on support vector machines [J]. J. Huazhong Univ. of Sci. & Tech. (Nature Science Edition), 2007 (05): 23-26.
[6] Guilherme Barreto Fernandes, Rinaldo Artes. Spatial dependence in credit risk and its improvement in credit scoring. 2016, 249 (2): 517-524.
[7] Fan Yanqin, Qin Yangsen, Yuan Yuan. Application of Bayesian network based on principal component analysis in personal credit evaluation [J]. Journal of Guilin University of Aerospace Technology, 2019, 24 (04): 568-575.
[8] Li Jin. Research on credit risk assessment of green credit based on random forest algorithm [J]. Financial theory and practice, 2015 (11): 14-18.
[9] Breiman L I, Friedman J H, Olshen R A, et al. Classification and Regression Trees (CART) [J]. Encyclopedia of Ecology, 1984, 40 (3): 582-588.
[10] Yang Guijun, Xu Xue, Zhao Fuqiang. Predicting User Ratings with XGBoost Algorithm [J]. Data analysis and knowledge discovery, 2019, 3 (01): 118-126.
[11] Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System [C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016: 785-794.
[12] Friedman J H. Greedy Function Approximation: A Gradient Boosting Machine [J]. Annals of Statistics, 2001, 29(5): 1189-1232.
[13] BAI Pengfei, AN Qi, Nicolaas Fransde ROOIJ, LI Nan, ZHOU Guofu. 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.
[14] Breiman L. Random Forests [J]. Machine Learning, 2001, 45(1): 5-32.
[15] Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System [C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016: 785-794.
[16] Zhang R, Gao Y, Yu W, et al. Review Comment Analysis for Predicting Ratings[A]// Web-Age Information Management [M]. Springer, 2015: 247-259.
[17] Chen T, Guestrin C., XGBoost: A Scalable Tree Boosting System [C] //Acm Sigkdd International Conference on Knowledge Discovery & Data Mining.2016.
[18] CHEN T Q, GUESTRIN C. XGBoost: a scalable tree boosting system [C] //Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 785-794.
[19] BREIMAN L. Random forests [J]. Machine Learning, 2001, 45: 5-32.

Downloads: 4081
Visits: 129394

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.