Explainability of Machine Learning Models for Bankruptcy Prediction
Open accessAbstract
As the amount of data increases, it is more likely that the assumptions in the existing economic analysis model are unsatisfied or make it difficult to establish a new analysis model. Therefore, there has been increased demand for applying the machine learning methodology to bankruptcy prediction due to its high performance. By contrast, machine learning models usually operate as black-boxes but credit rating regulatory systems require the provisioning of appropriate information regarding credit rating standards. If machine learning models have sufficient interpretablility, they would have the potential to be used as effective analytical models in bankruptcy prediction. From this aspect, we study the explainability of machine learning models for bankruptcy prediction by applying the Local Interpretable Model-Agnostic Explanations (LIME) algorithm, which measures the feature importance for each data point. To compare how the feature importance measured through LIME differs from that of models themselves, we first applied this algorithm to typical tree-based models that have ability to measure the feature importance of the models themselves. We showed that the feature importance measured through LIME could be a consistent generalization of the feature importance measured by tree-based models themselves. Moreover, we study the consistency of the feature importance through the model’s predicted bankruptcy probability, which suggests the possibility that observations of important features can be used as a basis for the fair treatment of loan eligibility requirements.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
XAI complements AI suggestions with explanations to ensure they are discrimination-free and thoroughly founded, rendering AI methods usable in the industry.
“XAI complements these suggestions with explanations to ensure they are discrimination-free and thoroughly founded, rendering the AI methods usable in the industry (Park et al. 2021).”
From Applications of Explainable Artificial Intelligence in Finance—a systematic review of Finance, Information Systems, and Computer Science literature (2024) · cites this paper as Park et al. 2021
ML has been most widely employed across client-facing operations in addition to anti-money laundering and anomaly detection.
“ML has been most widely employed across client-facing operations (including advertising and client support) in addition to anti-money laundering and anomaly detection.”
From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [77]
Several businesses also leverage ML in trading cost and implementation, credit risk analysis, and traditional insurance costing and screening.
“Several businesses also leverage ML in trading cost and implementation, credit risk analysis, and traditional insurance costing and screening [25], [77].”
From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [77]
Cites
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · see citing works
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555 · see citing works
An Analysis of Transformations
Box, G. E. P., & Cox, D. R. (1964) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.2517-6161.1964.tb00553.x · Cited by 15,059 · see citing works
FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY
Altman, E. I. (1968) · The Journal of Finance · doi:10.1111/j.1540-6261.1968.tb00843.x · Cited by 14,888 · see citing works
A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection
Kohavi, R. (1995) · Zenodo · doi:10.5281/zenodo.19712698 · Cited by 10,909 · see citing works
LightGBM: A Highly Efficient Gradient Boosting Decision Tree
(2017) · HAL · Cited by 10,512 · see citing works
Practical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691 · see citing works
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682 · see citing works
Financial Ratios and the Probabilistic Prediction of Bankruptcy
Ohlson, J. A. (1980) · Journal of Accounting Research · doi:10.2307/2490395 · Cited by 6,166 · see citing works
Methodological Issues Related to the Estimation of Financial Distress Prediction Models
Zmijewski, M. E. (1984) · Journal of Accounting Research · doi:10.2307/2490859 · Cited by 2,898 · see citing works
Explaining Explanations: An Overview of Interpretability of Machine Learning
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018) · 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00018 · Cited by 2,507 · see citing works
Machine Learning Interpretability: A Survey on Methods and Metrics
Carvalho, D. V., Pereira, E. M., & Cardoso, J. S. (2019) · Electronics · doi:10.3390/electronics8080832 · Cited by 1,842 · see citing works
ZETATM analysis A new model to identify bankruptcy risk of corporations
Altman, E. I., Haldeman, R. G., & Narayanan, P. (1977) · Journal of Banking & Finance · doi:10.1016/0378-4266(77)90017-6 · Cited by 1,828 · see citing works
Bankruptcy prediction in banks and firms via statistical and intelligent techniques – A review
Ravi Kumar, P., & Ravi, V. (2007) · European Journal of Operational Research · doi:10.1016/j.ejor.2006.08.043 · Cited by 1,074 · see citing works
Machine learning models and bankruptcy prediction
Barboza, F., Kimura, H., & Altman, E. I. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.04.006 · Cited by 1,006 · see citing works
Benchmarking state-of-the-art classification algorithms for credit scoring
Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., & Vanthienen, J. (2003) · Journal of the Operational Research Society · doi:10.1057/palgrave.jors.2601545 · Cited by 904 · see citing works
Solà, J., & Sevilla, J. (1997) · IEEE Transactions on Nuclear Science · doi:10.1109/23.589532 · Cited by 872 · see citing works
Bankruptcy prediction for credit risk using neural networks: A survey and new results
Atiya, A. F. (2001) · IEEE Transactions on Neural Networks · doi:10.1109/72.935101 · Cited by 699 · see citing works
A review on neural networks with random weights
Cao, W., Wang, X., Ming, Z., & Gao, J. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.08.040 · Cited by 472 · see citing works
Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction
Zięba, M., Tomczak, S. K., & Tomczak, J. M. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.04.001 · Cited by 422 · see citing works
A Review of Bankruptcy Prediction Studies: 1930 to Present
Gissel, J. L., Giacomino, D. E., & Akers, M. D. (2006) · e-Publications@Marquette (Marquette University) · Cited by 405 · see citing works
Financial ratios and corporate governance indicators in bankruptcy prediction: A comprehensive study
Liang, D., Lu, C.-C., Tsai, C.-F., & Shih, G.-A. (2016) · European Journal of Operational Research · doi:10.1016/j.ejor.2016.01.012 · Cited by 405 · see citing works
Systematic review of bankruptcy prediction models: Towards a framework for tool selection
Alaka, H., Oyedele, L. O., Owolabi, H. A., Kumar, P. V., Ajayi, S. O., Akinadé, O. O., & Bilal, M. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.10.040 · Cited by 331 · see citing works
Feature selection in bankruptcy prediction
Tsai, C. (2008) · Knowledge-Based Systems · doi:10.1016/j.knosys.2008.08.002 · Cited by 246 · see citing works
The effect of feature selection on financial distress prediction
Liang, D., Tsai, C., & Wu, H.-T. (2014) · Knowledge-Based Systems · doi:10.1016/j.knosys.2014.10.010 · Cited by 234 · see citing works
An improved boosting based on feature selection for corporate bankruptcy prediction
Wang, G., Ma, J., & Yang, S. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.09.033 · Cited by 187 · see citing works
The discovery of experts' decision rules from qualitative bankruptcy data using genetic algorithms
Kim, M.-J., & Han, I. (2003) · Expert Systems with Applications · doi:10.1016/s0957-4174(03)00102-7 · Cited by 180 · see citing works
Data analytic approach for bankruptcy prediction
Son, H., Hyun, C., Phan, D., & Hwang, H. J. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.07.033 · Cited by 142 · see citing works
Self-citationA unified view of gradient-based attribution methods for Deep Neural NetworksPreprint
Ancona, M., Ceolini, E., Öztireli, C., & Groß, M. H. (2017) · arXiv (Cornell University) · doi:10.3929/ethz-b-000237705 · Cited by 120 · see citing works
Non-iterative approaches in training feed-forward neural networks and their applications
Wang, X., & Cao, W. (2018) · Soft Computing · doi:10.1007/s00500-018-3203-0 · Cited by 48 · see citing works
Determinants of Corporate Bankruptcy: Evidence from Chaebol and Non‐Chaebol Firms in Korea
Kim, J. (2020) · Asian Economic Journal · doi:10.1111/asej.12218 · Cited by 8 · see citing works
Importance of Data Standardization in Privacy-Preserving K-Means Clustering
Su, C., Zhan, J., & Sakurai, K. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04205-8_23 · Cited by 7 · see citing works
An Evaluation of Bankruptcy Prediction Models Using Accounting and Market Information in Korea
Lee, I., & Kim, D. (2015) · Asian Review of Financial Research · Cited by 7 · see citing works
A Comparative Study on the Performance of Credit Evaluation Models
정완호, Kook, C.-P., & Hong, G. (2006) · Journal of Money & Finance · Cited by 2 · see citing works
Bae, Y.-I., Song, S.-H., Hong, S.-K., et al. (2008) · IE interfaces · Cited by 1 · see citing works
A Study on Financial Characteristic of Delisting Companies by KOSDAQ
Kim, J. H., Park, K.-I., & Choul, K. M. (2011) · Review of Accounting and Policy Studies · Cited by 1 · see citing works
Won, P. J., & 안성만 (2014) · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Review of Trustworthy and Explainable Artificial Intelligence (XAI)
Chamola, V., Hassija, V., Sulthana, A. R., Ghosh, D., Dhingra, D., & Sikdar, B. (2023) · IEEE Access · doi:10.1109/access.2023.3294569 · Cited by 352 · see citing works
Weber, P., Carl, K. V., & Hinz, O. (2024) · Management Review Quarterly · doi:10.1007/s11301-023-00320-0 · Cited by 292 · see citing works
“As our final set of articles reveals, only a few papers deal with whether the developed or applied XAI methods meet regulatory requirements (except for, e.g., Park et al. 2021).”
Influential
- Authors
- Park, M. S., Son, H., Hyun, C., & Hwang, H. J.
- Affiliations
- Pohang University of Science and Technology (KR)
- Corresponding author
- Hwang, Hyung Ju
- Venue
- IEEE Access
- Published
- 2021
- Volume
- 9
- Pages
- 124887-124899
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3198090055
- Cited by
- 83
- References
- 37
- Citations by year
- 2026: 14 · 2025: 24 · 2024: 21 · 2023: 19 · 2022: 4 · 2021: 1
- FWCI
- 3.98
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Open Access System for Information Sharing (Pohang University of Science and Technology) (submittedVersion)
- Funders
- National Research Foundation of Korea (NRF-2017R1E1A1A03070105, NRF-2019R1A5A1028324)
- Institute for Information and Communications Technology Promotion (2019-0-01906)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Business, Management and Accounting › Accounting › Financial Distress and Bankruptcy Prediction
- Social Sciences › Economics, Econometrics and Finance › Finance › Banking stability, regulation, efficiency
- Keywords
- bankruptcy prediction, explainability, lime, feature importance, tree-based models, black-box models, credit ratings, loan eligibility, credit risk provisioning, model interpretability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
