Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.94 MB
Add to list
  1. Search results
  2. Evaluating the stability of model exp...

Evaluating the stability of model explanations in instance-dependent cost-sensitive credit scoring

Matteo Ballegeer (UGent) , Matthias Bogaert (UGent) and Dries Benoit (UGent)
(2025) EUROPEAN JOURNAL OF OPERATIONAL RESEARCH. 326(3). p.630-640
Author
Organization
Abstract
Instance-dependent cost-sensitive (IDCS) classifiers offer a promising approach to improving cost-efficiency in credit scoring by tailoring loss functions to instance-specific costs. However, the impact of such loss functions on the stability of model explanations remains unexplored in literature, despite increasing regulatory demands for transparency. This study addresses this gap by evaluating the stability of Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) when applied to IDCS models. Using four publicly available credit scoring datasets, we first assess the discriminatory power and cost-efficiency of IDCS classifiers, introducing a novel metric to enhance cross-dataset comparability. We then investigate the stability of SHAP and LIME feature importance rankings under varying degrees of class imbalance through controlled resampling. Our results reveal that while IDCS classifiers improve cost-efficiency, they produce significantly less stable explanations compared to traditional models, particularly as class imbalance increases, highlighting a critical trade-off between cost optimization and interpretability in credit scoring. Amid increasing regulatory scrutiny on explainability, this research underscores the pressing need to address stability issues in IDCS classifiers to ensure that their cost advantages are not undermined by unstable or untrustworthy explanations.
Keywords
Analytics, Cost-sensitive learning, Credit scoring, Explainable AI, Explanation stability

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.94 MB

Citation

Please use this url to cite or link to this publication:

MLA
Ballegeer, Matteo, et al. “Evaluating the Stability of Model Explanations in Instance-Dependent Cost-Sensitive Credit Scoring.” EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, vol. 326, no. 3, 2025, pp. 630–40, doi:10.1016/j.ejor.2025.05.039.
APA
Ballegeer, M., Bogaert, M., & Benoit, D. (2025). Evaluating the stability of model explanations in instance-dependent cost-sensitive credit scoring. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 326(3), 630–640. https://doi.org/10.1016/j.ejor.2025.05.039
Chicago author-date
Ballegeer, Matteo, Matthias Bogaert, and Dries Benoit. 2025. “Evaluating the Stability of Model Explanations in Instance-Dependent Cost-Sensitive Credit Scoring.” EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 326 (3): 630–40. https://doi.org/10.1016/j.ejor.2025.05.039.
Chicago author-date (all authors)
Ballegeer, Matteo, Matthias Bogaert, and Dries Benoit. 2025. “Evaluating the Stability of Model Explanations in Instance-Dependent Cost-Sensitive Credit Scoring.” EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 326 (3): 630–640. doi:10.1016/j.ejor.2025.05.039.
Vancouver
1.
Ballegeer M, Bogaert M, Benoit D. Evaluating the stability of model explanations in instance-dependent cost-sensitive credit scoring. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH. 2025;326(3):630–40.
IEEE
[1]
M. Ballegeer, M. Bogaert, and D. Benoit, “Evaluating the stability of model explanations in instance-dependent cost-sensitive credit scoring,” EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, vol. 326, no. 3, pp. 630–640, 2025.
@article{01K075S64FMAQEMGTFGNZ2Z9ME,
  abstract     = {{Instance-dependent cost-sensitive (IDCS) classifiers offer a promising approach to improving cost-efficiency in credit scoring by tailoring loss functions to instance-specific costs. However, the impact of such loss functions on the stability of model explanations remains unexplored in literature, despite increasing regulatory demands for transparency. This study addresses this gap by evaluating the stability of Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) when applied to IDCS models. Using four publicly available credit scoring datasets, we first assess the discriminatory power and cost-efficiency of IDCS classifiers, introducing a novel metric to enhance cross-dataset comparability. We then investigate the stability of SHAP and LIME feature importance rankings under varying degrees of class imbalance through controlled resampling. Our results reveal that while IDCS classifiers improve cost-efficiency, they produce significantly less stable explanations compared to traditional models, particularly as class imbalance increases, highlighting a critical trade-off between cost optimization and interpretability in credit scoring. Amid increasing regulatory scrutiny on explainability, this research underscores the pressing need to address stability issues in IDCS classifiers to ensure that their cost advantages are not undermined by unstable or untrustworthy explanations.}},
  author       = {{Ballegeer, Matteo and Bogaert, Matthias and Benoit, Dries}},
  issn         = {{0377-2217}},
  journal      = {{EUROPEAN JOURNAL OF OPERATIONAL RESEARCH}},
  keywords     = {{Analytics,Cost-sensitive learning,Credit scoring,Explainable AI,Explanation stability}},
  language     = {{eng}},
  number       = {{3}},
  pages        = {{630--640}},
  title        = {{Evaluating the stability of model explanations in instance-dependent cost-sensitive credit scoring}},
  url          = {{http://doi.org/10.1016/j.ejor.2025.05.039}},
  volume       = {{326}},
  year         = {{2025}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: