Chinese Journal of Management Science ›› 2024, Vol. 32 ›› Issue (5): 1-12.doi: 10.16381/j.cnki.issn1003-207x.2021.0027
Xinnan Lei,Lefan Lin,Binqing Xiao(),Honghai Yu
Received:
2021-01-05
Revised:
2021-10-27
Online:
2024-05-25
Published:
2024-06-06
Contact:
Binqing Xiao
E-mail:bengking@nju.edu.cn
CLC Number:
Xinnan Lei,Lefan Lin,Binqing Xiao,Honghai Yu. Re-exploration of Small and Micro Enterprises' Default Characteristics Based on Machine Learning Models with SHAP[J]. Chinese Journal of Management Science, 2024, 32(5): 1-12.
"
指标类别 | 指标名称 | 说明 | 指标变量类型 |
---|---|---|---|
违约情况 | 贷款二项分类 | 1=逾期贷款,0=正常贷款 | |
贷款信息 | 贷款笔数 | 企业当前贷款笔数 | 连续型变量 |
贷款总额 | 企业收到的总贷款金额 | 连续型变量 | |
贷款利率 | 对于单笔贷款企业为该笔贷款年化利率,对于多笔贷款企业计算各笔贷款平均年化利率 | 连续型变量 | |
抵押贷款 | 1=抵押贷款,0=其他 | 类别型变量 | |
承兑汇票 | 1=承兑汇票贷款,0=无承兑汇票 | 类别型变量 | |
投向门类 | 指借款人将贷款投向的行业分类,包含农林牧渔业、采矿业、制造业、电业燃气及水的生产和供应业、建筑业、批发和零售业、交通运输仓储和邮政业、住宿和餐饮业、信息传输计算机服务和软件业、金融业、房地产业、租赁和商务服务业、科学研究和技术服务业、水利环境和公共设施管理业、居民服务修理业、教育、卫生和社会工作、文化体育和娱乐业、社会保障与社会组织 | 类别型变量 | |
自主支付 | 1=自主支付,0=受托支付 | 类别型变量 | |
经营用途 | 1=经营用途,0=固定资产用途 | 类别型变量 | |
企业财务 信息 | 资产总额 | 企业当前总资产 | 连续型变量 |
营业收入 | 本年度企业总收入 | 连续型变量 | |
注册资本 | 企业成立时注册资本 | 连续型变量 | |
企业非财务基本信息 | 企业年龄 | 从成立时刻起到贷款时刻的时长 | 连续型变量 |
行业门类 | 指借款人所处的行业分类,包含农林牧渔业、采矿业、制造业、电业燃气及水的生产和供应业、建筑业、批发和零售业、交通运输仓储和邮政业、住宿和餐饮业、信息传输计算机服务和软件业、金融业、房地产业、租赁和商务服务业、科学研究和技术服务业、水利环境和公共设施管理业、居民服务修理业、教育、卫生和社会工作、文化体育和娱乐业、社会保障与社会组织 | 类别型变量 | |
企业类型 | 指借款人所属的组织形式,包含个体、有限责任、股份和其他 | 类别型变量 | |
控股主体 | 1=国有或集体控股,0=私人控股 | 类别型变量 | |
控股性质 | 1=绝对控股,0=非绝对控股 | 类别型变量 | |
所属区域 | 1=城镇企业,0=乡村企业 | 类别型变量 | |
从业人数 | 企业当前员工总数 | 连续型变量 | |
企业非财务行为信息 | 被告案件数量 | 涉及法律诉讼中企业作为被告次数 | 连续型变量 |
原告案件数量 | 涉及法律诉讼中企业作为原告次数 | 连续型变量 | |
企业评级软信息 | 客户经理对客户信用的主观评价 | 客户经理主观评价是指企业借贷时客户经理对借款企业当前经济效益、履约能力和商业信誉等要素的主观判断,包含优秀、较好、一般、不佳、恶化、关停 | 类别型变量 |
"
指标名称 | 统计量 | 模型名称 | |||||
---|---|---|---|---|---|---|---|
逻辑回归 | XGBoost | LightGBM | 随机森林 | Adaboost | GBDT | ||
AUC | 均值 | 0.7268 | 0.8075 | 0.8161 | 0.8084 | 0.8015 | 0.7925 |
标准差 | 0.0687 | 0.0442 | 0.0419 | 0.0420 | 0.0504 | 0.0466 | |
Accuracy | 均值 | 0.8891 | 0.9075 | 0.9083 | 0.9015 | 0.9063 | 0.9045 |
标准差 | 0.0188 | 0.0137 | 0.0153 | 0.0112 | 0.0107 | 0.0090 | |
Precision | 均值 | 0.3214 | 0.4381 | 0.4428 | 0.4000 | 0.4309 | 0.4190 |
标准差 | 0.1195 | 0.0868 | 0.0966 | 0.0714 | 0.0681 | 0.0590 | |
Recall | 均值 | 0.3068 | 0.4181 | 0.4227 | 0.3818 | 0.4113 | 0.4000 |
标准差 | 0.1141 | 0.0829 | 0.0922 | 0.0682 | 0.0651 | 0.0563 | |
F1 Score | 均值 | 0.3139 | 0.4279 | 0.4325 | 0.3906 | 0.4209 | 0.4093 |
标准差 | 0.1167 | 0.0848 | 0.0944 | 0.0698 | 0.0665 | 0.0576 |
"
样本集合 | 指标名称 | 不同样本划分下平均排名 | 总计平均排名 | ||||
---|---|---|---|---|---|---|---|
XGBoost | LightGBM | 随机森林 | Adaboost | GBDT | |||
训练集 | 企业年龄 | 1.15 | 1.90 | 1.25 | 1.00 | 1.35 | 1.33 |
营业收入 | 2.60 | 3.25 | 3.70 | 2.55 | 2.95 | 3.01 | |
被告案件数量 | 3.30 | 5.75 | 2.05 | 6.15 | 2.70 | 3.99 | |
还款利率 | 3.90 | 2.65 | 4.50 | 5.25 | 5.15 | 4.29 | |
借款总额 | 5.15 | 5.20 | 3.65 | 5.90 | 5.00 | 4.98 | |
从业人数 | 6.20 | 5.70 | 6.90 | 2.70 | 7.25 | 5.75 | |
注册资本 | 7.35 | 5.45 | 6.80 | 7.20 | 6.10 | 6.58 | |
自主支付 | 6.75 | 6.95 | 7.90 | 10.20 | 6.50 | 7.66 | |
资产总额 | 8.60 | 8.15 | 8.90 | 5.25 | 8.05 | 7.79 | |
客户经理对客户信用的主观评价 | 10.30 | 11.40 | 12.45 | 10.80 | 11.15 | 11.22 | |
测试集 | 企业年龄 | 1.15 | 1.95 | 1.35 | 1.30 | 1.30 | 1.41 |
营业收入 | 2.75 | 3.50 | 3.75 | 3.25 | 3.20 | 3.29 | |
被告案件数量 | 3.05 | 4.90 | 2.05 | 6.55 | 2.30 | 3.77 | |
还款利率 | 4.25 | 2.95 | 4.40 | 4.25 | 5.35 | 4.24 | |
借款总额 | 5.15 | 5.55 | 3.75 | 6.30 | 5.00 | 5.15 | |
从业人数 | 6.25 | 5.95 | 6.90 | 1.85 | 7.20 | 5.63 | |
注册资本 | 7.20 | 5.25 | 6.80 | 7.45 | 6.15 | 6.57 | |
自主支付 | 6.65 | 6.85 | 7.65 | 10.35 | 6.75 | 7.65 | |
资产总额 | 8.55 | 8.10 | 8.80 | 7.10 | 7.80 | 8.07 | |
客户经理对客户信用的主观评价 | 10.25 | 11.40 | 12.35 | 10.70 | 11.15 | 11.17 |
1 | 中国人民银行,中国银行保险监督管理委员会. 中国小微企业金融服务报告[M].北京:中国金融出版社,2019. |
The People's Bank of China, China Banking and Insurance Regulatory Commission. Financial services report for China's small and micro enterprises[M]. Beijing: China Financial Publishing House, 2019. | |
2 | Altman E I. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy[J]. The Journal of Finance, 1968, 23(4): 589-609. |
3 | Minnis M, Sutherland A. Financial statements as monitoring mechanisms: Evidence from small commercial loans[J]. Journal of Accounting Research, 2017, 55(1): 197-233. |
4 | Pederzoli C, Torricelli C. A parsimonious default prediction model for Italian SMEs[R]. Working Paper, 2010. |
5 | 迟国泰,李鸿禧. 基于逐步判别分析的小企业债信评级模型及实证[J].管理工程学报,2019,33(4):205-215. |
Chi G T, Li H X.Small enterprise credit rating model and empirical evidence based on stepwise discriminant analysis[J]. Journal of Industrial Engineering and Engineering Management,2019,33(4): 205-215. | |
6 | Van Laere E, Baesens B. The development of a simple and intuitive rating system under Solvency II[J].Insurance: Mathematics and Economics, 2010, 46(3): 500-510. |
7 | Altman E I, Sabato G, Wilson N. The value of non-financial information in small and medium-sized enterprise risk management[J]. Journal of Credit Risk, 2012, 6(2):95-127. |
8 | 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. The credit rating model of rural households' small loans based on ELECTRE III[J]. Journal of Systems & Management,2018,27(5):854-862. | |
9 | Moro A, Fink M. Loan managers’ trust and credit access for SMEs[J]. Journal of Banking & Finance, 2013, 37(3): 927-936. |
10 | Berger A N, Klapper L F, Udell G F. The ability of banks to lend to informationally opaque small businesses[J]. Journal of Banking & Finance, 2001, 25(12): 2127-2167. |
11 | Berger A N, Udell G F. Small business credit availability and relationship lending: The importance of bank organisational structure[J]. The Economic Journal, 2002, 112(477): F32-F53. |
12 | 于善丽,迟国泰,姜欣.基于指标体系违约鉴别能力最大的小企业债信评级体系及实证[J].中国管理科学,2020,28(6):38-50. |
Yu S L, Chi G T, Jiang X. Small enterprise credit rating system and its empirical evidence based on the indicator system's default identification ability[J]. Chinese Journal of Management Science,2020,28(6):38-50. | |
13 | Li B, Xiao B, Yang Y. Strengthen credit scoring system of small and micro businesses with soft information: Analysis and comparison based on neural network models[J]. Journal of Intelligent and Fuzzy Systems, 2021(40):4257-4274. |
14 | 熊熊,马佳,赵文杰,等. 供应链金融模式下的信用风险评价 [J]. 南开管理评论,2009,12(4): 92 - 98. |
Xiong X, Ma J, Zhao W J, et al. Credit risk evaluation under the supply chain finance model [J]. Nankai Business Review, 2009, 12(4): 92-98. | |
15 | Saygili E, Saygili A T, Gokhan I. An analysis of factors affecting credit scoring performance in SMEs[J]. Ege Academic Review, 2019, 19(2): 159-171. |
16 | 肖斌卿,杨旸,余哲,等. 小微企业信用评级模型及比较研究[J].系统工程学报,2016,31(6):798-807+830. |
Xiao B Q, Yang Y, Yu Z, et al. Small and micro enterprise credit rating models and comparative research[J]. Journal of Systems Engineering, 2016,31(6): 798-807+830. | |
17 | 肖斌卿,杨旸,李心丹,等. 基于模糊神经网络的小微企业信用评级研究[J].管理科学学报,2016,19 (11):114-126. |
Xiao B Q, Yang Y, Li X D, et al. Study on the credit rating of small and micro enterprises based on fuzzy neural network[J]. Journal of Management Sciences in China,2016,19(11):114-126. | |
18 | Teles G, Rodrigues J J P C, Saleem K, et al. Machine learning and decision support system on credit scoring[J]. Neural Computing and Applications, 2020, 32(14): 9809-9826. |
19 | 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 evidence based on Focal Loss modified cross-entropy loss function[J]. Chinese Journal of Management Science,2022,30(5):65-75. | |
20 | 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. SVM classification of unbalanced customer credit risk of microfinance companies based on improved SMOTE[J]. Chinese Journal of Management Science, 2016, 24(3): 24-30. | |
21 | Bao W, Lianju N, Yue K. Integration of unsupervised and supervised machine learning algorithms for credit risk assessment[J]. Expert Systems with Applications, 2019, 128: 301-315. |
22 | Gulsoy N, Kulluk S. A data mining application in credit scoring processes of small and medium enterprises commercial corporate customers[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2019, 9(3): e1299. |
23 | Pławiak P, Abdar M, Pławiak J, et al. DGHNL: A new deep genetic hierarchical network of learners for prediction of credit scoring[J]. Information Sciences, 2020, 516: 401-418. |
24 | Breiman L. Statistical modeling: The two cultures (with comments and a rejoinder by the author)[J]. Statistical Science, 2001, 16(3): 199-231. |
25 | 高俊光,刘旭,朱辰辰. 小微企业信用评估的数据挖掘方法综述[J].金融理论与实践,2015(10):98-101. |
Gao J G, Liu X, Zhu C C. Summary of data mining methods for credit evaluation of small and micro enterprises[J].Financial Theory & Practice, 2015(10):98-101. | |
26 | 孔祥维,唐鑫泽,王子明. 人工智能决策可解释性的研究综述[J].系统工程理论与实践,2021,41(2):524-536. |
Kong X W, Tang X Z, Wang Z M. A survey of research on the explainability of artificial intelligence decision-making[J]. System Engineering Theory and Practice, 2021,41(2):524-536. | |
27 | 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. Personal characteristics of executives and company performance: Empirical evidence based on machine learning[J]. Journal of Management Sciences in China,2020,23(2):120-140. | |
28 | Gu S, Kelly B, Xiu D. Empirical asset pricing via machine learning[J]. The Review of Financial Studies, 2020, 33(5): 2223-2273. |
29 | 周矍铄. 大型互联网企业进入金融领域的潜在风险与监管[N].金融时报,2020-11-01(观点·实践). |
Zhou J S. Potential risks and supervision of large Internet companies entering the financial field[N]. Financial News, 2020-11-01 (View·Practice). | |
30 | 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, San Francisco, USA,13-17 August, ACM, 2016: 785-794. |
31 | Lundberg S M, Lee S I. A unified approach to interpreting model predictions[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, 4-9 December, NeurIPS, 2017:4768-4777. |
32 | Shapley L S. A value for n-person games[J]. Contributions to the Theory of Games, 1953,2(28): 307-317. |
33 | Maschler M, Peleg B, Shapley L S. The kernel and bargaining set for convex games[J]. International Journal of Game Theory, 1971, 1(1): 73-93. |
34 | Lundberg S M, Erion G, Chen H, et al. From local explanations to global understanding with explainable AI for trees[J]. Nature Machine Intelligence, 2020, 2(1): 56-67. |
35 | Liberti J M, Petersen M A. Information: Hard and soft[J]. Review of Corporate Finance Studies, 2019, 8(1): 1-41. |
36 | 满向昱,张天毅,汪川,等.我国中小微企业信用风险因素识别及测度研究[J].中央财经大学学报,2018(9):46-58. |
Man X Y, Zhang T Y, Wang C, et al. Research on the identification and measurement of credit risk factors of China's small, medium and micro enterprises[J]. Journal of Central University of Finance & Economics,2018(9):46-58. | |
37 | Blanco A, Pino-Mejías R, Lara J, et al. Credit scoring models for the microfinance industry using neural networks: Evidence from peru[J]. Expert Systems with Applications, 2013, 40(1): 356-364. |
38 | Hastie T, Tibshirani R, Friedman J H, et al. The elements of statistical learning: Data mining, inference, and prediction[M]. New York: Springer, 2009. |
39 | Thomas L C. A survey of credit and behavioral scoring: Forecasting financial risk of lending to consumers[J]. International Journal of Forecasting, 2000, 16(2): 149-172. |
[1] | Weizhen Rao,Xiaohe Miao,lu Liu. Research on Collaborative Distribution Model Considering Distribution Capability Constraints of Enterprises and Its Influence on Cost Allocation [J]. Chinese Journal of Management Science, 2024, 32(7): 106-116. |
[2] | Yue Zhao,Yanzhi Wang,Jie Song,Xuan He. Research on Data Value Based on Demand Forecast of Online Medical Platform [J]. Chinese Journal of Management Science, 2024, 32(7): 28-36. |
[3] | Liangyan Tao,Li Wang,Xiaoxia Qi,Ding Chen,Sifeng Liu. On Grey Shapley Value Model for Evaluating the Contribution Rate of Weapon Equipment System [J]. Chinese Journal of Management Science, 2024, 32(4): 89-96. |
[4] | Hongmei Guo,Menglin Qin,Xianyu Wang,Meng Wu. Does Fixed-Rate Loans Help Small and Mirco Retailers with Insufficient Operational Capitals? [J]. Chinese Journal of Management Science, 2024, 32(1): 177-186. |
[5] | Yuting Yan,Wenjie Bi. A Data-driven Single-Period Newsvendor Problem Based on XGBoost Algorithm [J]. Chinese Journal of Management Science, 2024, 32(1): 260-267. |
[6] | Er-fang SHAN. The Cooperative Game Approach for River Flooding Risk [J]. Chinese Journal of Management Science, 2023, 31(9): 45-51. |
[7] | LI Qing, GE Xiang-yu, XIANG Xiu-li. Nonparametric Option Pricing under Multivariate No-arbitrage Constraints [J]. Chinese Journal of Management Science, 2023, 31(7): 60-67. |
[8] | NI Xuan-ming, QIU Yu-ning, ZHAO Hui-min. The Mechanism and Solution of Equity Gap in Private Equity Market [J]. Chinese Journal of Management Science, 2023, 31(7): 91-102. |
[9] | LIANG Mo, LI Hong-xiang, ZHANG Shun-ming. A Measure for Financial Distress based on ST Predictive Model and the Cross-section of Stock Returns [J]. Chinese Journal of Management Science, 2023, 31(2): 138-149. |
[10] | Peng ZHANG,Shi-li DANG,Mei-yu HUANG,Jing-xin LI. Two-stage Mean Semi-variance Portfolio Optimization with Stock Return Prediction Using Machine Learning [J]. Chinese Journal of Management Science, 2023, 31(12): 96-106. |
[11] | Jian ZHANG,Ting-yu XIE,Peng PENG,Hong-wei WANG. Research on the Correlation between Product Knowledge Attributes and Sales Forecast in Multi-Value Chain Collaborative Data Space of Manufacturing Industry [J]. Chinese Journal of Management Science, 2023, 31(11): 341-348. |
[12] | LI Zhen-ping, YI Ming-chao. Research on the Location-Distribution Problem of Distribution Centers Based on “Self-operating + Outsourcing” Mode Under Uncertain Demands [J]. Chinese Journal of Management Science, 2022, 30(8): 143-154. |
[13] | LIU De-wen, GAO Wei-he, MIN Liang-yu. The Impact of Readability and Attractiveness on Product Sales——Text Analysis Based on Movie Introduction [J]. Chinese Journal of Management Science, 2022, 30(6): 167-177. |
[14] | LIANG Chao, WEI Yu, MA Feng, LI Xia-fei. Forecasting Volatility of China Gold Futures Price: New Evidence from Model Shrinkage Methods [J]. Chinese Journal of Management Science, 2022, 30(4): 30-41. |
[15] | LI Bing, DANG Jia-jun, XUAN Hua. Optimization of Simultaneous Placing-in and Taking-out Wagons with Multiple Engines on Branch-shaped Siding [J]. Chinese Journal of Management Science, 2022, 30(4): 228-239. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||
|