A Review of Computational Models for Corporate Credit Rating

doi:10.11871/jfdc.issn.2096-742X.2023.04.012

Abstract

Abstract:

[Objective] Corporate credit rating is important to social economics and this paper aims to introduce the main methods for corporate credit rating in the era of artificial intelligence and big data. [Methods] This paper systematically reviews the main methods and databases of corporate credit rating through paper reading and investigation, including statistical models, machine learning models, and neural network models. Both advantages and disadvantages of these models are compared. Finally, the existing problems and future work in corporate credit rating are pointed out. [Results] This paper provides a good introduction to computational models and databases of corporate credit rating for both academia and industry. [Conclusions] There are still some problems with neural network models in corporate credit rating and dynamic graph neural networks are promising to better address the challenges in corporate credit rating.

Key words: corporate credit rating, statistical method, machine learning, neural network

TIAN Yiqing, CHENG Xi, FENG Bojing. A Review of Computational Models for Corporate Credit Rating[J]. Frontiers of Data and Computing, 2023, 5(4): 139-153, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2023.04.012.

Figures/Tables 3

Table 1

Table 2

Fig.1

References 52

[1]	Hajek P, Michalak K. Feature selection in corporate credit rating prediction[J]. Knowledge-Based Systems, 2013, 51: 72-84. doi: 10.1016/j.knosys.2013.07.008
[2]	Kim K, Ahn H. A corporate credit rating model using multi-class support vector machines with an ordinal pairwise partitioning approach[J]. Computers & Operations Research, 2012, 39(8): 1800-1811. doi: 10.1016/j.cor.2011.06.023
[3]	Huang Z, Chen H, Hsu C J, et al. Credit rating analysis with support vector machines and neural networks: a market comparative study[J]. Decision support systems, 2004, 37(4): 543-558. doi: 10.1016/S0167-9236(03)00086-1
[4]	Altman E I, Haldeman R G, Narayanan P. ZETATM analysis A new model to identify bankruptcy risk of corporations[J]. Journal of banking & finance, 1977, 1(1): 29-54. doi: 10.1016/0378-4266(77)90017-6
[5]	Yurdakul M, Ic Y T. Development of a performance measurement model for manufacturing companies using the AHP and TOPSIS approaches[J]. International Journal of Production Research, 2005, 43(21): 4609-4641. doi: 10.1080/00207540500161746
[6]	Gu W, Basu M, Chao Z, et al. A unified framework for credit evaluation for internet finance companies: Multi-criteria analysis through AHP and DEA[J]. International Journal of Information Technology & Decision Making, 2017, 16(3): 597-624.
[7]	Yang S, Islam M T. Principal Component Analysis and Factor Analysis for Feature Selection in Credit Rating[EB/OL].[2020-12-21]. https://arxiv.org/abs/2011.09137.
[8]	Reichert A K, Cho C C, Wagner G M. An examination of the conceptual issues involved in developing credit-scoring models[J]. Journal of Business & Economic Statistics, 1983, 1(2): 101-114.
[9]	Altman E I, Saunders A. Credit risk measurement: Developments over the last 20 years[J]. Journal of banking & finance, 1997, 21(11-12): 1721-1742. doi: 10.1016/S0378-4266(97)00036-8
[10]	Friedman J H. Multivariate adaptive regression splines[J]. The annals of statistics, 1991, 19(1): 1-67.
[11]	Laitinen E K. Predicting a corporate credit analyst’s risk estimate by logistic and linear models[J]. International review of financial analysis, 1999, 8(2): 97-121. doi: 10.1016/S1057-5219(99)00012-5
[12]	West R C. A factor-analytic approach to bank condition[J]. Journal of Banking & Finance, 1985, 9(2): 253-266. doi: 10.1016/0378-4266(85)90021-4
[13]	Liang X, Chen S, Liu Y. The study of small enterprises credit evaluation based on incremental AntClust[C]. 2007 IEEE International Conference on Grey Systems and Intelligent Services, IEEE, 2007: 294-298.
[14]	Shi B, Meng B, Yang H, et al. A novel approach for reducing attributes and its application to small enterprise financing ability evaluation[J]. Complexity, 2018, 2018: 1-17.
[15]	Ic Y T, Yurdakul M. Development of a quick credibility scoring decision support system using fuzzy TOPSIS[J]. Expert Systems with Applications, 2010, 37(1): 567-574. doi: 10.1016/j.eswa.2009.05.038
[16]	Wang Y, Wang S, Lai K K. A new fuzzy support vector machine to evaluate credit risk[J]. IEEE Transactions on Fuzzy Systems, 2005, 13(6): 820-831. doi: 10.1109/TFUZZ.2005.859320
[17]	Cao L, Guan L K, Jingqing Z. Bond rating using support vector machine[J]. Intelligent Data Analysis, 2006, 10(3): 285-296. doi: 10.3233/IDA-2006-10307
[18]	Lee Y C. Application of support vector machines to corporate credit rating prediction[J]. Expert Systems with Applications, 2007, 33(1): 67-74. doi: 10.1016/j.eswa.2006.04.018
[19]	Huang C L, Chen M C, Wang C J. Credit scoring with a data mining approach based on support vector machines[J]. Expert systems with applications, 2007, 33(4): 847-856. doi: 10.1016/j.eswa.2006.07.007
[20]	Zhu P, Hu Q. Rule extraction from support vector mach-ines based on consistent region covering reduction[J]. Knowledge-Based Systems, 2013, 42: 1-8. doi: 10.1016/j.knosys.2012.12.003
[21]	Maldonado S, Pérez J, Bravo C. Cost-based feature selection for support vector machines: An application in credit scoring[J]. European Journal of Operational Research, 2017, 261(2): 656-665. doi: 10.1016/j.ejor.2017.02.037
[22]	Gu T, Yang S. Duration prediction for truck crashes based on the XGBoost algorithm[M]. CICTP 2019, 2019: 5021-5031.
[23]	Florez-Lopez R, Ramon-Jeronimo J M. Enhancing accuracy and interpretability of ensemble strategies in credit risk assessment. A correlated-adjusted decision forest proposal[J]. Expert Systems with Applications, 2015, 42(13): 5737-5753. doi: 10.1016/j.eswa.2015.02.042
[24]	Yeh C C, Lin F, Hsu C Y. A hybrid KMV model, random forests and rough set theory approach for credit rating[J]. Knowledge-Based Systems, 2012, 33: 166-172. doi: 10.1016/j.knosys.2012.04.004
[25]	Abellán J, Castellano J G. A comparative study on base classifiers in ensemble methods for credit scoring[J]. Expert systems with applications, 2017, 73: 1-10. doi: 10.1016/j.eswa.2016.12.020
[26]	Donate J P, Cortez P, Sanchez G G, et al. Time series forecasting using a weighted cross-validation evo-lutionary artificial neural network ensemble[J]. Neuro-computing, 2013, 109: 27-32.
[27]	Yu L, Wang S, Lai K K. Credit risk assessment with a multistage neural network ensemble learning approach[J]. Expert systems with applications, 2008, 34(2): 1434-1444. doi: 10.1016/j.eswa.2007.01.009
[28]	He H, Zhang W, Zhang S. A novel ensemble method for credit scoring: Adaption of different imbalance ratios[J]. Expert Systems with Applications, 2018, 98: 105-117. doi: 10.1016/j.eswa.2018.01.012
[29]	Chornous G, Nikolskyi I. Business-oriented feature selection for hybrid classification model of credit scoring[C]. 2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP), IEEE, 2018: 397-401.
[30]	Wang M, Ku H. Utilizing historical data for corporate credit rating assessment[J]. Expert Systems with Appli-cations, 2021, 165: 113925.
[31]	Chen Y S, Cheng C H. Hybrid models based on rough set classifiers for setting credit rating decision rules in the global banking industry[J]. Knowledge-Based Systems, 2013, 39: 224-239. doi: 10.1016/j.knosys.2012.11.004
[32]	Chai N, Wu B, Yang W, et al. A multicriteria approach for modeling small enterprise credit rating: evidence from China[J]. Emerging Markets Finance and Trade, 2019, 55(11): 2523-2543. doi: 10.1080/1540496X.2019.1577237
[33]	Chen B, Long S. A novel end-to-end corporate credit rating model based on self-attention mechanism[J]. IEEE Access, 2020, 8: 203876-203889. doi: 10.1109/Access.6287639
[34]	Golbayani P, Wang D, Florescu I. Application of deep neural networks to assess corporate credit rating[EB/OL]. [2020-3-4]. https://arxiv.org/abs/2003.02334.
[35]	Brennan D, Brabazon A. Corporate Bond Rating Using Neural Networks[C]. IC-AI, 2004: 161-167.
[36]	Angelini E, Di Tollo G, Roli A. A neural network approach for credit risk evaluation[J]. The quarterly review of economics and finance, 2008, 48(4): 733-755. doi: 10.1016/j.qref.2007.04.001
[37]	Choi J, Suh Y, Jung N. Predicting corporate credit rating based on qualitative information of MD&A transformed using document vectorization techniques[J]. Data Technologies and Applications, 2020, 54(2): 151-168. doi: 10.1108/DTA-08-2019-0127
[38]	Du Y. Enterprise credit rating based on genetic neural network[C]. MATEC Web of Conferences. EDP Sciences, 2018, 227: 02011.
[39]	Luo C, Wu D, Wu D. A deep learning approach for credit scoring using credit default swaps[J]. Engineering Applications of Artificial Intelligence, 2017, 65: 465-470. doi: 10.1016/j.engappai.2016.12.002
[40]	Kim K S. Predicting bond ratings using publicly available information[J]. Expert Systems with Applications, 2005, 29(1): 75-81. doi: 10.1016/j.eswa.2005.01.007
[41]	Hájek P. Probabilistic Neural Networks for Credit Rating Modelling[C]. IJCCI (ICFC-ICNC), 2010: 289-294.
[42]	Fu K, Cheng D, Tu Y, et al. Credit card fraud detection using convolutional neural networks[C]. International conference on neural information processing, Springer, Cham, 2016: 483-490.
[43]	Rajaa S, Sahoo J K. Convolutional feature extraction and neural arithmetic logic units for stock prediction[C]. International Conference on Advances in Computing and Data Sciences, Springer, Singapore, 2019: 349-359.
[44]	Dixon M, Klabjan D, Bang J H. Classificationbased fin-ancial markets prediction using deep neural networks[J]. Algorithmic Finance, 2017, 6(3-4): 67-77. doi: 10.3233/AF-170176
[45]	Feng B, Xue W, Xue B, et al. Every corporation owns its image: Corporate credit ratings via convolutional neural networks[C]. 2020 IEEE 6th International Conference on Computer and Communications (ICCC), IEEE, 2020: 1578-1583.
[46]	Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space[EB/OL]. [2014-9-7]. https://arxiv.org/abs/1301.3781.
[47]	Le Q, Mikolov T. Distributed representations of sentences and documents[C]. International conference on machine learning, PMLR, 2014: 1188-1196.
[48]	Feng B, Xu H, Xue W, et al. Every corporation owns its structure: Corporate credit ratings via graph neural networks[EB/OL]. [2020-11-27]. https://arxiv.org/abs/2012.01933.
[49]	Feng B, Xue W. Adversarial semi-supervised learning for corporate credit ratings[J]. The Journal of Software, 2021, 16(6): 259-266.
[50]	Feng B, Xue W. Contrastive Pre-training for Imbalanced Corporate Credit Ratings[EB/OL]. [2022-2-23]. https://arxiv.org/abs/2102.12580.
[51]	Plumb G, Molitor D, Talwalkar A S. Model agnostic supervised local explanations[J]. Advances in neural information processing systems, 2018, 31: 1-10.
[52]	Wang D, Chen Z, Florescu I. A Sparsity Algorithm with Applications to Corporate Credit Rating[EB/OL]. [2021-7-21]. https://arxiv.org/abs/2107.10306.

数据库	简介
RESSET	中国的一个综合性数据平台，提供全世界金融市场相关数据；主要包括股票、黄金、研究报告、宏观统计等系列
上市公司财务报告	上市公司对企业生产经营概况、财务状况等信息进行披露的报告
中国人民银行征信系统	中国国内最全的企业和个人征信数据库
CSMAR	针对中国国情开发的经济金融领域的研究型精准数据库，2001年创建；涵盖因子研究、绿色经济、股票、资讯、基金等18大系列，包含160多个数据库、4,000多张表、5万多个字段
WRDS	由宾夕法尼亚大学沃顿商学院于1993年开发的金融领域的跨库研究工具，整合了Compustat、CRSP、TFN、TAQ等多个著名数据库
Bloomberg	全球最大的财经资讯、金融数据服务提供商
FAME	覆盖了英国和爱尔兰的380万家公司的信息
UCI机器学习知识库	加州大学欧文分校提出的用于机器学习的数据库
Compustat	标准普尔发布的数据库，收录北美及全球上市公司近20年的财务数据
CRSP	由芝加哥大学商学研究生院成立，是证券领域极具权威的数据库，广泛收录了美国上市公司的股票价格和交易数据
日经NEEDS	日本最大的综合经济数据库，涵盖了从宏观经济到企业财务多个层面
Bankscope	BureauvanDijk与银行业权威评级机构惠誉公司合作开发的银行业信息库；提供了全球12,800多家主要银行及世界重要金融机构与组织的经营与信用分析数据
WIND	由中国企业万得资讯提供，是以金融证券财经数据为核心的数据库
KIS-VALUE	韩国一个提供企业报务报表及股市数据分析的数据库

类别	指标
规模	总资产
	总资本
	总现金流
	权益总额
	资本支出总额
	市值
	总交易量
	债务总额
盈利能力	息税前收益
	税后收入
	净利润增长
	净资产销售额
	总资产销售额
	非现金营运资本
	上一年的销售
股市	红利
	每股收益的增长
	市盈率
	留存收益
	股价
	已发行股份数量