Interpretive Ensemble Framework for Credit Default Risk Forecasting
Keywords:
Ensemble framework, interpretive models, dependency driven, explainable models, stacked ensembleAbstract
In the realm of financial decision-making, particularly within the banking and investment sectors, credit default risk forecasting holds immense significance. The evolving landscape of financial markets has introduced heightened intricacies and interconnections among financial instruments, rendering the task of accurate credit risk assessment increasingly daunting. Conventional statistical models often fall short in capturing the dynamic essence of credit risk, thereby fueling a surge in interest towards more sophisticated methodologies such as ensemble learning frameworks. This paper presents a meticulous review and analysis of interpretive ensemble frameworks tailored for credit default risk forecasting. Introducing a multistage ensemble framework, augmented with dependency-driven explainable techniques, this research offers a novel approach. Evaluation outcomes underscore the superiority of the Proposed Algorithm, surpassing both individual base classifiers and other ensemble models across various metrics. Noteworthy is its exceptional precision, recall, F1-score, and accuracy, positioning it as a standout choice for credit risk prediction. The heightened precision underscores its capacity for accurate positive instance predictions, while the robust recall emphasizes its ability to capture nearly all positive instances. Additionally, this research introduces a Dependency-based Explainable Model meticulously crafted to enhance the interpretability of machine learning models, particularly focusing on multistage heterogeneous stacked ensembles. Despite the significant enhancements in predictive capabilities brought about by these ensemble models, their complexity often presents challenges in understanding individual contributions to final predictions. The Dependency-based Explainable Model addresses this interpretability gap by systematically identifying and elucidating dependencies between input variables, stages, and models within the ensemble.
Downloads
References
A. Bhattacharya, S. K. Biswas, and A. Mandal, “Credit risk evaluation: a comprehensive study,” Multimedia Tools and Applications 2022, pp. 1–51, Oct. 2022, doi: 10.1007/S11042-022-13952-3.
T. M. Yhip and B. M. D. Alagheband, “Statistical Methods of Credit Risk Analysis,” in The Practice of Lending, Springer International Publishing, 2020, pp. 351–381. doi: 10.1007/978-3-030-32197-0_8.
K. Jajuga, “Statistical Methods in Credit Risk Analysis,” Prace Naukowe Akademii Ekonomicznej we Wrocławiu. Taksonomia, vol. 8, no. nr 906 Klasyfikacja i analiza danych : teoria i zastosowania, pp. 224–232, 2001.
M. Psillaki, I. E. Tsolas, and D. Margaritis, “Evaluation of credit risk based on firm performance.”
A. Caldarelli, C. Fiondella, M. Maffei, and C. Zagaria, “Managing risk in credit cooperative banks: Lessons from a case study,” Management Accounting Research, vol. 32, pp. 1–15, 2016, doi: 10.1016/j.mar.2015.10.002.
L. Jinjuan, “Research on enterprise credit risk assessment method based on improved genetic algorithm,” in Proceedings - 9th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2017, Institute of Electrical and Electronics Engineers Inc., Jan. 2017, pp. 215–218. doi: 10.1109/ICMTMA.2017.0058.
C. Li, Q. Liu, and L. Huang, “Credit risk management of scientific and technological enterprises based on text mining,” Enterp Inf Syst, 2020, doi: 10.1080/17517575.2020.1802514.
R. Kanapickiene and R. Spicas, “Credit risk assessment model for small and micro-enterprises: The case of Lithuania,” Risks, vol. 7, no. 2, p. 67, Jun. 2019, doi: 10.3390/risks7020067.
“DEVELOPMENT OF ENTERPRISE CREDIT RISK ASSESSMENT MODEL FOR LITHUANIAN CREDIT UNIONS.” Accessed: Jun. 06, 2021. [Online]. Available: https://web.b.ebscohost.com/abstract?direct=true&profile=ehost&scope=site&authtype=crawler&jrnl=16484460&AN=130816055&h=pnjbxWpMnulvfDF%2FwTHv4%2FV1OtA9WFHpfU3InY7Gx6XM5tKRyfsJlE3RQtjO1DCWtP8tedF2DWzdETafHje55A%3D%3D&crl=c&resultNs=AdminWebAuth&resultLoca
M. Papouskova and P. Hajek, “Two-stage consumer credit risk modelling using heterogeneous ensemble learning,” Decis Support Syst, vol. 118, pp. 33–45, Mar. 2019, doi: 10.1016/j.dss.2019.01.002.
M. Shahhosseini, G. Hu, and H. Pham, “Optimizing ensemble weights and hyperparameters of machine learning models for regression problems,” Machine Learning with Applications, vol. 7, 2022, doi: 10.1016/j.mlwa.2022.100251.
F. Divina, A. Gilson, F. Goméz-Vela, M. G. Torres, and J. F. Torres, “Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting,” Energies 2018, Vol. 11, Page 949, vol. 11, no. 4, p. 949, Apr. 2018, doi: 10.3390/EN11040949.
M. Abdoli, M. Akbari, and J. Shahrabi, “Dynamic Ensemble Learning for Credit Scoring: A Comparative Study,” 2020, Accessed: May 16, 2021. [Online]. Available: https://arxiv.org/abs/2010.08930v1
X. Huang, X. Liu, and Y. Ren, “Enterprise credit risk evaluation based on neural network algorithm,” Cogn Syst Res, vol. 52, pp. 317–324, Dec. 2018, doi: 10.1016/j.cogsys.2018.07.023.
X. Huang, X. Liu, and Y. Ren, “Enterprise credit risk evaluation based on neural network algorithm,” Cogn Syst Res, vol. 52, pp. 317–324, Dec. 2018, doi: 10.1016/j.cogsys.2018.07.023.
V. García, A. I. Marqués, and J. S. Sánchez, “Exploring the synergetic effects of sample types on the performance of ensembles for credit risk and corporate bankruptcy prediction,” Information Fusion, vol. 47, pp. 88–101, May 2019, doi: 10.1016/j.inffus.2018.07.004.
G. Wang and J. Ma, “A hybrid ensemble approach for enterprise credit risk assessment based on Support Vector Machine,” Expert Syst Appl, vol. 39, no. 5, pp. 5325–5331, Apr. 2012, doi: 10.1016/J.ESWA.2011.11.003.
X. Huang, X. Liu, and Y. Ren, “Enterprise credit risk evaluation based on neural network algorithm,” Cogn Syst Res, vol. 52, pp. 317–324, Dec. 2018, doi: 10.1016/j.cogsys.2018.07.023.
D. J. Hand and W. E. Henley, “Statistical classification methods in consumer credit scoring: A review,” J R Stat Soc Ser A Stat Soc, vol. 160, no. 3, pp. 523–541, Sep. 1997, doi: 10.1111/j.1467-985X.1997.00078.x.
A. Hooman, G. Marthandan, W. F. W. Yusoff, M. Omid, and S. Karamizadeh, “Statistical and data mining methods in credit scoring,” The Journal of Developing Areas, vol. 50, no. 5, pp. 371–381, 2016, doi: 10.1353/jda.2016.0057.
J. Galindo and P. Tamayo, “Credit risk assessment using statistical and machine learning: Basic methodology and risk modeling applications,” Comput Econ, vol. 15, no. 1–2, pp. 107–143, 2000, doi: 10.1023/a:1008699112516.
J. C. K. Chow, “Analysis of Financial Credit Risk Using Machine Learning,” Feb. 2018, doi: 10.13140/RG.2.2.30242.53449.
W. M. Mou, W. K. Wong, and M. McAleer, “Financial credit risk evaluation based on core enterprise supply chains,” Sustainability (Switzerland), vol. 10, no. 10, p. 3699, Oct. 2018, doi: 10.3390/su10103699.
Y. Song, Y. Wang, X. Ye, D. Wang, Y. Yin, and Y. Wang, “Multi-view ensemble learning based on distance-to-model and adaptive clustering for imbalanced credit risk assessment in P2P lending,” Inf Sci (N Y), vol. 525, pp. 182–204, Jul. 2020, doi: 10.1016/j.ins.2020.03.027.
S. R. Lenka, S. K. Bisoy, R. Priyadarshini, and M. Sain, “Empirical Analysis of Ensemble Learning for Imbalanced Credit Scoring Datasets: A Systematic Review,” Wirel Commun Mob Comput, vol. 2022, 2022, doi: 10.1155/2022/6584352.
S. Wei, D. Yang, W. Zhang, and S. Zhang, “A novel noise-adapted two-layer ensemble model for credit scoring based on backflow learning,” IEEE Access, vol. 7, pp. 99217–99230, 2019, doi: 10.1109/ACCESS.2019.2930332.
H. He and Y. Fan, “A novel hybrid ensemble model based on tree-based method and deep learning method for default prediction,” Expert Syst Appl, vol. 176, Aug. 2021, doi: 10.1016/j.eswa.2021.114899.
L. M. Demajo, V. Vella, and A. Dingli, “Explainable AI for Interpretable Credit Scoring,” ArXiv, pp. 185–203, Dec. 2020, doi: 10.5121/csit.2020.101516.
R. Confalonieri, L. Coba, B. Wagner, and T. R. Besold, “A historical perspective of explainable Artificial Intelligence,” WILEs Data Mining and Knowledge Discovery, vol. 11, no. 1, Jan. 2021, doi: 10.1002/widm.1391.
N. L. Torrent, G. Visani, and E. Bagli, “PSD2 Explainable AI Model for Credit Scoring,” ArXiv, Nov. 2020, Accessed: Apr. 27, 2021. [Online]. Available: http://arxiv.org/abs/2011.10367
N. Bussmann, P. Giudici, D. Marinelli, and J. Papenbrock, “Explainable Machine Learning in Credit Risk Management,” Comput Econ, vol. 57, no. 1, pp. 203–216, Jan. 2021, doi: 10.1007/s10614-020-10042-0.
C. Chen, K. Lin, C. Rudin, Y. Shaposhnik, S. Wang, and T. Wang, “An Interpretable Model with Globally Consistent Explanations for Credit Risk,” NIPS 2018 Workshop on Challenges and Opportunities for AI in Financial Services: the Impact of Fairness, Explainability, Accuracy, and Privacy, Montréal, Canada. 2018.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
