Identification and loss measurement of credit risk on rural households' farmland management right mortgages based on the machine learning

PENG Yanling, PENG Yijie, ZHOU Hongli, WANG Shouyang, JIANG Yuansheng

Systems Engineering - Theory & Practice ›› 2025, Vol. 45 ›› Issue (2) : 448-462.

PDF(1349 KB)
中国科学院数学与系统科学研究院期刊网
PDF(1349 KB)
Systems Engineering - Theory & Practice ›› 2025, Vol. 45 ›› Issue (2) : 448-462. DOI: 10.12011/SETP2023-1141

Identification and loss measurement of credit risk on rural households' farmland management right mortgages based on the machine learning

  • PENG Yanling1, PENG Yijie2,3, ZHOU Hongli4, WANG Shouyang5,6,7, JIANG Yuansheng8
Author information +
History +

Abstract

Using the survey data collected from rural households in Ningxia, Chongqing, and Sichuan provinces, this paper has identified the credit risk and measured the risk loss, under the context of land property rights controlled and the imperfect ecology of rural finance market in China. This paper uses machine learning method to identify farmers' credit risk and verifies the effectiveness of this method compared with the traditional model. Also, Credit Risk+ model is employed to evaluate farmers' credit risk. According to the survey statistics, the default rate of farmers' farmland management right mortgages is relatively high, and it was 10%. Results show that the random forest model could identify the key factors of credit risk and predict the default probability effectively. Moreover, the expected loss and risk exposure of each loan is relatively high, and the risk loss increases rapidly under the impact of extreme events. In addition, it is helpful for financial institutions to optimize the financial capital structure and improve the risk management strategy to increase the investigation of farmers' passive default motivation under the prior risk management framework. Thus, we conclude with several policy implications such as the accelerating development of fintech, improvement of rural credit investigation system, and innovation of risk pre-warning tools.

Key words

farmland management rights mortgage / credit risk of rural household / risk identification / loss measurement / machine learning

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
PENG Yanling , PENG Yijie , ZHOU Hongli , WANG Shouyang , JIANG Yuansheng. Identification and loss measurement of credit risk on rural households' farmland management right mortgages based on the machine learning. Systems Engineering - Theory & Practice, 2025, 45(2): 448-462 https://doi.org/10.12011/SETP2023-1141

References

[1] Zhang H, Luo J, Cheng M, et al. How does rural household differentiation affect the availability of farmland management right mortgages in China?[J]. Emerging Markets Finance and Trade, 2019, 56(11): 2509-2528.
[2] 顾庆康, 林乐芬. 农地经营权抵押贷款能缓解异质性农户信贷配给难题吗?[J]. 经济评论, 2019(5): 63-76. Gu Q K, Lin L F. Can farmland management rights mortgages relieve the credit rationing of farmers?[J]. Economic Review, 2019(5): 63-76.
[3] 吕德宏, 张无坷. 农地经营权抵押贷款信用风险影响因素及其衡量研究——基于CreditRisk+模型的估计[J]. 华中农业大学学报(社会科学版), 2018(4): 137-147. Lü D H, Zhang W K. Influential factors and measuring of credit risk on farmland contract right mortgage loan—Estimation based on Credit Risk+ model[J]. Journal of Huazhong Agricultural University (Social Sciences Edition), 2018(4): 137-147.
[4] 王珏, 范静. 农地经营权担保有效性与借款人还款表现——一个基于"资产主导型"农地经营权抵押贷款的证据[J]. 农业技术经济, 2019(10): 38-52. Wang J, Fan J. Collateral efficiency of farmland operational right and borrowers' repayment performance[J]. Journal of Agrotechnical Economics, 2019(10): 38-52.
[5] 张苏江, 陈庭强. 对数Gauss衰减的信用风险传染模型与CDO定价研究[J]. 北京理工大学学报(社会科学版), 2014, 16(3): 83-88. Zhang S J, Chen T Q. Credit risk contagion model based on logarithmic Gauss distribution and CDO pricing[J]. Journal of Beijing Institute of Technology (Social Sciences Edition), 2014, 16(3): 83-88.
[6] 赵志冲, 迟国泰, 白雪鹏. 基于最小显著差异法农户关键违约特征挖掘[J]. 系统工程理论与实践, 2020, 40(9): 2339-2351. Zhao Z C, Chi G T, Bai X P. Mining the key default characteristics of loan farmers based on the least significant different method[J]. Systems Engineering—Theory & Practice, 2020, 40(9): 2339-2351.
[7] 石宝峰, 王静. 基于ELECTRE III的农户小额贷款信用评级模型[J]. 系统管理学报, 2018, 27(5): 854-862. Shi B F, Wang J. A credit rating model of microfinance for farmers based on ELECTRRE III[J]. Journal of Systems & Management, 2018, 27(5): 854-862.
[8] 程砚秋, 徐占东. 基于泰尔指数修正的ELECTRE III 小企业信用评价模型[J]. 中国管理科学, 2019, 27(10): 22-33. Cheng Y Q, Xu Z D. Credit risk evaluation of small enterprises based on revised ELECTRRE III by Theil index[J]. Chinese Journal of Management Science, 2019, 27(10): 22-33.
[9] 杨莲, 石宝峰, 迟国泰, 等. 非均衡数据下基于BPNN-LDAMCE的信用评级模型设计及应用[J]. 数量经济技术经济研究, 2022, 39(3): 152-169. Yang L, Shi B F, Chi G T, et al. Design and application of a credit rating model based on BPNN-LDAMCE with imbalanced data[J]. Journal of Quantitative & Technological Economics, 2022, 39(3): 152-169.
[10] 曾燕, 杨雅婷, 徐凤敏, 等. 消费金融研究综述[J]. 系统工程理论与实践, 2022, 42(1): 84-109. Zeng Y, Yang Y T, Xu F M, et al. Survey of consumer finance research[J]. Systems Engineering—Theory & Practice, 2022, 42(1): 84-109.
[11] 姜富伟, 薛浩, 周明. 大数据提升了多因子模型定价能力吗? —— 基于机器学习方法对我国A股市场的探究[J]. 系统工程理论与实践, 2022, 42(8): 2037-2048. Jiang F W, Xue H, Zhou M. Does big data improve multi-factor asset pricing models? Exploration of China's A-share market with machine learning[J]. Systems Engineering—Theory & Practice, 2022, 42(8): 2037-2048.
[12] 陆瑶, 张叶青, 黎波, 等. 高管个人特征与公司业绩——基于机器学习的经验证据[J]. 管理科学学报, 2020, 23(2): 120-140. Lu Y, Zhang Y Q, Li B, et al. Managerial individual characteristics and corporate performance: Evidence from a machine learning approach[J]. Journal of Management Sciences in China, 2020, 23(2): 120-140.
[13] Wager S, Athey S. Estimation and inference of heterogeneous treatment effects using random forests[J]. Journal of the American Statistical Association, 2018, 113(523): 1228-1242.
[14] 刘景江, 郑畅然, 洪永淼. 机器学习如何赋能管理学研究? 国内外前沿综述和未来展望[J]. 管理世界, 2023(9): 191-215. Liu J J, Zheng C R, Hong Y M. How can machine learning empower management research? A domestic-foreign frontier review and future prospects[J]. Journal of Management World, 2023(9): 191-215.
[15] 王达, 周映雪. 随机森林模型在宏观审慎监管中的应用——基于18个国家数据的实证研究[J]. 国际金融研究, 2020(11): 45-54. Wang D, Zhou Y X. Application of random forest model in macro prudential regulation—An empirical study based on the data of 18 countries[J]. Studies of International Finance, 2020(11): 45-54.
[16] Nagel S. Machine learning in asset pricing[M]. Princeton: Princeton University Press, 2021.
[17] Du Jardin P. A two-stage classification technique for bankruptcy prediction[J]. European Journal of Operational Research, 2016, 254(1): 236-252.
[18] 黄益平, 邱晗. 大科技信贷: 一个新的信用风险管理框架[J]. 管理世界, 2021, 37(2): 12-21. Huang Y P, Qiu H. Big tech lending: A new credit risk management framework[J]. Journal of Management World, 2021, 37(2): 12-21.
[19] Gambacorta L, Huang Y, Qiu H, et al. How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm[R]. BIS Working Papers, 2019, 834.
[20] Berg T, Burg V, Gombović A, et al. On the rise of fintechs: Credit scoring using digital footprints[J]. The Review of Financial Studies, 2020, 33(7): 2845-2897.
[21] Kozak S, Nagel S, Santosh T. Shrinking the cross-section[J]. Journal of Finance Economics, 2020, 135(2): 271-292.
[22] 洪永淼、汪寿阳: 大数据如何改变经济学研究范式?[J]. 管理世界, 2021(10): 40-55. Hong Y, Wang S. How is big data changing economic research paradigms?[J]. Journal of Management World, 2021(10): 40-55.
[23] Chen J, Katchova A L, Zhou C. Agricultural loan delinquency prediction using machine learning methods[J]. International Food and Agribusiness Management Review, 2021, 24(5): 797-812.
[24] Huang Y, Zhang L, Li Z, et al. Fintech credit risk assessment for SMEs: Evidence from China[R]. IMF Working Papers, 2020(193): 1-42.
[25] 杨奇才, 谢璐, 韩文龙. 农地经营权抵押贷款的实现与风险: 实践与案例评析[J]. 农业经济问题, 2015, 36(10): 4-11. Yang Q C, Xie L, Han W L. The realization and risk of mortgage loan based on agricultural land using rights: A comment on the practices and case[J]. Issues in Agricultural Economy, 2015, 36(10): 4-11.
[26] 常露露, 吕德宏. 农地经营权抵押贷款风险识别及其应用研究——基于重庆639个农户样本调查数据[J]. 大连理工大学学报(社会科学版), 2018, 39(5): 41-50. Chang L L, Lü D H. Risk identification of mortgage loans for farmland management right and its application—Based on a survey of 639 farming households in Chongqing[J]. Journal of Dalian University of Technology (Social Sciences), 2018, 39(5): 41-50.
[27] Nikhade D M, Shinde P S, Nighot S M. Crop loan repayment behavior in cotton growers[J]. Agricultural Banker, 1994, 11(1): 13-16.
[28] Njoku J E. Determinants of loan repayment under the special emergency loan scheme (SEALS) in Niger: A case study in IMO state[J]. African Review of Money Finance and Banking, 1997(1): 39-51.
[29] Katchova A L, Barry P J. Credit risk models and agricultural lending[J]. American Journal of Agricultural Economics, 2005, 87(1): 194-205.
[30] Sileshi M, Nyikal R, Wangia S. Factors affecting loan repayment performance of smallholder farmers in east Hararghe, Ethiopia[J]. Developing Country Studies, 2012, 2(11): 205-214.
[31] Karlan D R, Osei I, Osei-Akoto, et al. Agricultural decisions after relaxing credit and risk constraints[J]. Quarterly Journal of Economics, 2014, 129(2): 597-652.
[32] Shi B, Zhao X, Wu B, et al. Credit rating and microfinance lending decision based on loss given default (LGD)[J]. Finance Research Letters, 2019(30): 124-129.
[33] 吕德宏, 朱莹. 农户小额信贷风险影响因素层次差异性研究[J]. 管理评论, 2017, 29(1): 33-41. Lü D H, Zhu Y. Research on the factors and hierarchy difference of farmer household microfinance risk[J]. Mana- gement Review, 2017, 29(1): 33-41.
[34] 谢云峰, 彭振江, 谢港华. 信用贷款的违约风险必然较高吗?——基于中小银行逐笔贷款数据的实证研究[J]. 南方金融, 2022(3): 28-40. Xie Y F, Peng Z J, Xie G H. Is the default risk of credit loans necessarily higher?[J]. South China Finance, 2022(3): 28-40.
[35] 杨莲, 石宝峰. 基于Focal Loss修正交叉熵损失函数的信用风险评价模型及实证[J]. 中国管理科学, 2022, 30(5): 65-75. Yang L, Shi B F. Credit risk evaluation model and empirical research based on focal loss modified cross-entropy loss function[J]. Chinese Journal of Management Science, 2022, 30(5): 65-75.
[36] 杨栋, 张建龙. 农户信贷有风险吗——基于CreditMetrics模型的分析[J]. 山西财经大学学报, 2009, 31(3): 85-89. Yang D, Zhang J L. Do farmer credit have risk—A study based on rural credit cooperative in institution[J]. Journal of Shanxi University of Finance and Economics, 2009, 31(3): 85-89.
[37] 吕志华, 彭建刚. CreditRisk+模型采用Poisson分布所产生的经济资本计量误差分析[J]. 管理评论, 2011, 23(1): 33-40. Lü Z H, Peng J G. Analysis of economic capital calculation error by Poisson distribution applied in Credit Risk+ model[J]. Management Review, 2011, 23(1): 33-40.
[38] 苏治, 胡迪. 农户信贷违约都是主动违约吗? —— 非对称信息状态下的农户信贷违约机理[J]. 管理世界, 2014(9): 77-89. Su Z, Hu D. Do farmer's default actively in loan? The mechanism of farmers' credit default under asymmetric information state[J]. Journal of Management World, 2014(9): 77-89.
[39] 衣柏衡, 朱建军, 李杰. 基于改进SMOTE的小额贷款公司客户信用风险非均衡SVM分类[J]. 中国管理科学, 2016, 24(3): 24-30. Yi B H, Zhu J J, Li J. Imbalanced data classification on micro-credit company customer credit risk assessment using improved SMOTE support vector machine[J]. Chinese Journal of Management Science, 2016, 24(3): 24-30.
[40] 迟国泰, 潘明道, 程砚秋. 基于综合判别能力的农户小额贷款信用评价模型[J]. 管理评论, 2015, 27(6): 42-57. Chi G T, Pan M D, Cheng Y Q. Credit rating model of small loans for farmers based on comprehensive discriminate capacity[J]. Management Review, 2015, 27(6): 42-57.
[41] Pes B. Ensemble feature selection for high-dimensional data: A stability analysis across multiple domains[J]. Neural Computing & Applications, 2020, 32: 5951-5973.
[42] 杨鸿雁, 田英杰. 机器学习在食品安全风险预警及抽检方案制订中的应用研究[J]. 管理评论, 2022(11): 315-323. Yang H Y, Tian Y J. Application research of machine learning in food safety risk early warning and sampling inspection program[J]. Management Review, 2022(11): 315-323.
[43] 马晓君, 董碧滢, 王常欣. 一种基于PSO优化加权随机森林算法的上市公司信用评级模型设计[J]. 数量经济技术经济研究, 2019, 36(12): 165-182. Ma X J, Dong B Y, Wang C X. Design of a credit rating model of quoted companies based on the PSO optimized weighted random forest algorithm[J]. Journal of Quantitative & Technological Economics, 2019, 36(12): 165-182.
[44] Vandendorpe A, Ho N, Vanduffel S, et al. On the parameterization of the CreditRisk+ model for estimating credit portfolio risk[J]. Insurance: Mathematics and Economics, 2007, 42(2): 736-745.
[45] Pederson G D, Zech L. Assessing credit risk in an agricultural loan portfolio[J]. Canadian Journal of Agricultural Economics, 2009, 57(2): 169-185.

Funding

National Natural Science Foundation of China (71903141, 72325007, 72022001, 72250065)
PDF(1349 KB)

537

Accesses

0

Citation

Detail
Sections
Recommended

/

〈 〉