Micro and small enterprises default risk portrait: evidence from explainable machine learning method

被引：2
作者：
Zheng C. [1 ]
Weng F. [2 ,3 ,4 ]
Luo Y. [5 ]
Yang C. [6 ]
机构：
[1] Public Administration Department, Fujian Police College, Fuzhou
[2] National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen
[3] School of Medicine, Xiamen University, Xiamen
[4] Data Mining Research Center, Xiamen University, Xiamen
[5] Xiaomi Technology Co., Ltd, Beijing
[6] College of Tourism, Hunan Normal University, Changsha
来源：
Journal of Ambient Intelligence and Humanized Computing | 2024年 / 15卷 / 01期
关键词：
Default risk prediction; Machine learning; SHAP method; User portrait theory;
D O I：
10.1007/s12652-023-04722-6
中图分类号：
学科分类号：
摘要：
Default risk prediction presents a significant challenge for micro and small enterprises due to the unavailability of comprehensive information databases. This paper develops a default risk management tool based on user portrait theory, utilizing common and objective indicators of micro and small enterprises, such as basic information about entrepreneurs, enterprises, and loans. The Shapley Additive exPlanations (SHAP) method is employed to analyze the contribution of each indicator to default prediction. Empirical results show that household income and personal income are the two most important variables in general, with higher household income associated with a lower probability of default. However, a higher personal income is associated with a higher probability of default. Moreover, the importance of variables and the direction of their relationship with default prediction vary across samples. These findings provide significant insights for developing an accurate default prediction warning system for financial institution managers and policymakers, using the proposed methodology and technical framework. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.
引用
收藏
页码：661 / 671
页数：10
相关论文
共 60 条
  • [41] Molnar C., Interpretable Machine Learning, (2020)
  • [42] Moscatelli M., Parlapiano F., Narizzano S., Corporate default forecasting with machine learning, Expert Syst Appl, 161, (2020)
  • [43] Moya-Carvajal J., Perez-Galarce F., Taramasco C., ML models for severity classification and length-of-stay forecasting in emergency units, Expert Systems with Applications, (2023)
  • [44] Ochoa J.G.D., Maier L., Csiszar O., Bayesian Logical Neural Networks for Human-Centered Applications in Medicine, (2021)
  • [45] Ohlson J.A., Financial ratios and the probabilistic prediction of bankruptcy, J Account Res, pp. 109-131, (1980)
  • [46] Oni O.A., Oladele O.I., Oyewole I.K., Analysis of factors influencing loan default among poultry farmers in ogun state nigeria, J Central Euro Agricult, 6, 4, pp. 619-624, (2006)
  • [47] Petropoulos A., Chatzis S.P., Xanthopoulos S., A novel corporate credit rating system based on Student’st hidden Markov models, Expert Syst Appl, 53, pp. 87-105, (2016)
  • [48] Puri M., Rocholl J., Steffen S., What do a million observations have to say about loan defaults? Opening the black box of relationships, J Financial Intermediation, 31, pp. 1-15, (2017)
  • [49] Shapley L.S., Stochastic games, Proc Natl Acad Sci, 39, 10, pp. 1095-1100, (1953)
  • [50] Sohn S.Y., Kim D.H., Yoon J.H., Technology credit scoring model with fuzzy logistic regression, Appl Soft Comput, 43, pp. 150-158, (2016)
123456