Prediction of personal default risks based on a sparrow search algorithm with support vector machine model

Xu Shen; Xinyu Wang; Xu Shen; Xinyu Wang

doi:10.3934/mbe.2023858

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 11: 19401-19415. doi: 10.3934/mbe.2023858

Previous Article Next Article

Research article Special Issues

Prediction of personal default risks based on a sparrow search algorithm with support vector machine model

Xu Shen ^{1,2
,
,},
Xinyu Wang ¹

1.
School of Economics and Management, China University of Mining and Technology, Xuzhou 221116, China
2.
School of Economics, Shandong Women's University, Jinan 250300, China

Academic Editor: Jorge Bernardino

Received: 11 July 2023 Revised: 27 September 2023 Accepted: 08 October 2023 Published: 19 October 2023

Aiming at the personal credit evaluation of commercial banks, this paper constructs a classified prediction model based on machine learning methods to predict the default risk. At the same time, this paper proposes to combine the sparrow search algorithm (SSA) with the support vector machine (SVM) to explore the application of the SSA-SVM model in personal default risk prediction. Therefore, this paper takes the personal credit data as the original data, carries out statistical analysis, normalization and principal factor analysis, and substitutes the obtained variables as independent variables into the SSA-SVM model. Under the premise of the same model, the experimental results show that the evaluation indexes of the experimental data are better than the original data, which shows that it is effective for the data processing operation of the original data in this paper. On the premise of the same data, each evaluation index of the SSA-SVM model is better than the SVM model, which shows that the hybridized model established in this paper is better than the latter one in predicting personal default risk, and has certain practical value.
- default risks,
- SSA-SVM model,
- credit assessment,
- prediction accuracy,
- commercial banks
Citation: Xu Shen, Xinyu Wang. Prediction of personal default risks based on a sparrow search algorithm with support vector machine model[J]. Mathematical Biosciences and Engineering, 2023, 20(11): 19401-19415. doi: 10.3934/mbe.2023858

Related Papers:

Abstract

Aiming at the personal credit evaluation of commercial banks, this paper constructs a classified prediction model based on machine learning methods to predict the default risk. At the same time, this paper proposes to combine the sparrow search algorithm (SSA) with the support vector machine (SVM) to explore the application of the SSA-SVM model in personal default risk prediction. Therefore, this paper takes the personal credit data as the original data, carries out statistical analysis, normalization and principal factor analysis, and substitutes the obtained variables as independent variables into the SSA-SVM model. Under the premise of the same model, the experimental results show that the evaluation indexes of the experimental data are better than the original data, which shows that it is effective for the data processing operation of the original data in this paper. On the premise of the same data, each evaluation index of the SSA-SVM model is better than the SVM model, which shows that the hybridized model established in this paper is better than the latter one in predicting personal default risk, and has certain practical value.

References

[1]	L. C. Thomas, A survey of credit and behavioural scoring: Forecasting financial risk of lending to consumers, Int. J. Forecast., 16 (2000), 149–172. https://doi.org/10.1016/S0169-2070(00)00034-0 doi: 10.1016/S0169-2070(00)00034-0
[2]	X. Q. Zhang, Research on Credit Risk Measurement and Management of Commercial Banks in China, Ph.D thesis, Harbin Engineering University, 2011. https://doi.org/10.7666/d.Y2236459
[3]	S. Finlay, Multiple classifier architectures and their application to credit risk assessment, Eur. J. Oper. Res., 210 (2011), 368–378. https://doi.org/10.1016/j.ejor.2010.09.029 doi: 10.1016/j.ejor.2010.09.029
[4]	D. Durand, Risk elements in consumer instalment financing, in NBER Books, 1941.
[5]	F. Andersson, H. Mausser, D. Rosen, S. V. Uryasev, Credit risk optimization with conditional value-at-risk criterion, Math. Prog., 89 (2001), 273–291. https://doi.org/10.1007/PL00011399 doi: 10.1007/PL00011399
[6]	Q. Shi, Y. Jin, Consumer credit scoring model: A survey, Stat. Res., 8 (2003), 36–39.
[7]	Z. G. Du, Overview of personal credit assessment and data mining, South China Financ. Comput., 3 (2004), 8–11. https://doi.org/10.3969/j.issn.2095-0799.2004.03.004 doi: 10.3969/j.issn.2095-0799.2004.03.004
[8]	V. Vapnik, The Nature of Statistical Learning Theory, Springer-Verlag, New York, (1995), 1–314. https://doi.org/10.1007/978-1-4757-2440-0_1
[9]	W. U. Chong, Y. Wang, Y. M. Guo, The model of personal credit risk assessment on support vector machine, Oper. Res. Manage., 4 (2008).
[10]	Z. Y. Guo, Using support vector machine for the credit evaluation, Comput. Knowl. Technol., 5 (2009).
[11]	J. W. Tian, Application of support vector machine and logistic regression model in the forecast of personal credit, Reg. Finance Res., 11 (2018), 25–30.
[12]	H. L. Tang, B. Q. He, Z. Wei, Research on SVM-based credit evaluation model for bank personal loans, West. Econ. Manage. Forum, 23 (2012), 7. https://doi.org/10.3969/j.issn.2095-1124.2012.01.011 doi: 10.3969/j.issn.2095-1124.2012.01.011
[13]	C. H. Shen, G. L. Liu, N. Y. Deng, An improved support vector classification and its application, Comput. Eng., 8 (2005). https://doi.org/10.1038/sj.cr.7290370
[14]	B. Zhong, Z. Xiao, C. L. Liu, L. Chen, The credit evaluation method based on LS-SVM, Stat. Res., 11 (2005).
[15]	Z. Xiao, W. J. Li, Personal credit scoring based on PCA and SVM, Technol. Econ., 29 (2010).
[16]	D. P. Dai, L. P. Ni, M. Xue, Application of bank personal credit rating model based on k-means and SVM, J. Jiangsu Univ. Sci. Technol., 31 (2017), 836–842.
[17]	X. Y. Liu, Y. M. Wang, Evaluation model for personal credit risk based on C4.5 algorithm for optimizing SVM, Comput. Syst. Appl., 28 (2019), 6.
[18]	H. Wang, Research on personal credit assessment model based on SVM, Sci. Technol. Entrepreneurship Mon., 32 (2019).
[19]	Q. Li, Logistic and SVM credit score models based on lasso variable selection, J. Appl. Math. Phys., 7 (2019), 1131–1148. https://doi.org/10.1007/S12190-023-01877-5 doi: 10.1007/S12190-023-01877-5
[20]	Y. Wang, Y. F. Lu, Personal credit risk evaluation of SVM optimization based on shuffled frog leaping algorithm, Heilongjiang Sci., 11 (2020), 2.
[21]	J. J. Chen, S. Liu, Personal credit evaluation based on SVM optimized by improved beetle swarm optimization algorithm, Comput. Technol. Dev., 31 (2021), 5. https://doi.org/10.3969/j.issn.1673-629X.2021.06.024 doi: 10.3969/j.issn.1673-629X.2021.06.024
[22]	J. K. Xue, B. Shen, A novel swarm intelligence optimization approach: Sparrow search algorithm, Syst. Sci. Control Eng., 8 (2020), 22–34. https://doi.org/10.1080/21642583.2019.1708830 doi: 10.1080/21642583.2019.1708830
[23]	S. X. Wang, M. Zeng, Research on rural road cost forecast based on SSA optimized BP neural network, Eng. Econ., 31 (2021), 25–29. https://doi.org/10.19298/j.cnki.1672-2442.202108025 doi: 10.19298/j.cnki.1672-2442.202108025
[24]	Y. H. Liang, S. Y. Mao, J. F. Li, Research on rock burst data based on SSA optimized BP neural network, Electron. Test., 36 (2022), 3.
[25]	H. Z. Hu, C. Qin, F. Guan, H. B. Zhang, S. J. An, Tool wear recognition based on sparrow search algorithm optimized support vector machine, Sci. Technol. Eng., 21 (2021), 10755–10761. https://doi.org/10.3969/j.issn.1671-1815.2021.25.026 doi: 10.3969/j.issn.1671-1815.2021.25.026
[26]	W. G. Wang, Y. B. Wei, X. D. Teng, Y. Huang, Short-term wind turbine generation power prediction based on sparrow search optimization support vector machine, Intell. Comput. Appl., 12 (2022), 012.
[27]	L. Thomas, J. Crook, D. Edelman, Credit scoring and its applications, Soc. Ind. Appl. Math., 2017. https://doi.org/10.1137/1.9781611974560 doi: 10.1137/1.9781611974560
[28]	R. A. Anderson, Credit Intelligence & Modelling: Many Paths Through the Forest of Credit Rating and Scoring, Oxford University Press, 2022 https://doi.org/10.1093/oso/9780192844194.001.0001
[29]	D. B. Ntwiga, Social Network Analysis for Credit Risk Modeling, Ph.D. thesis, University of Nairobi, 2016.
[30]	G. Paleologo, A. Elisseeff, G. Antonini, Subagging for credit scoring models, Eur. J. Oper. Res., 201 (2010), 490–499. https://doi.org/10.1016/j.ejor.2009.03.008 doi: 10.1016/j.ejor.2009.03.008
[31]	S. Figini, P. Giudici, Statistical merging of rating models, J. Oper. Res. Soc., 62 (2011), 1067–1074. https://doi.org/10.1057/jors.2010.41 doi: 10.1057/jors.2010.41

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)