Beyond Accuracy: A Multi-Dimensional Explainability and Model-Risk Framework for AI-Based Credit Decisions in Banking
Computer and Decision Making: An International Journal · 07.11.2026 · 3 (6S) · 2519-2550
DOI: 10.1922/comdem.v3i6s.19001 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer and Decision Making: An International Journal, online erschienen am 07.11.2026. Verfasst von Anamika und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Beyond predictive discrimination, selecting AI models for mortgage lending requires examining explainability, fairness, calibration, stability, and governance. This study proposes a Beyond-Accuracy, Interpretability and Model-Risk Scoring (BAIMRS) framework and analyzes recorded decisions for 9,360,942 applications in the 2025 Home Mortgage Disclosure Act (HMDA) data. These labels describe historical lender denials, not borrower default; public HMDA data do not include credit scores. Four algorithms (Logistic Regression, Random Forest, XGBoost, and LightGBM) were compared with a monotone LightGBM benchmark on a locked test cohort of 1,211,242 applications and three same-year institution holdouts. LightGBM had the highest ROC-AUC (0.8729) and precision-recall AUC (0.7696), narrowly ahead of XGBoost (0.8727, 0.7688); their paired AUC difference was 0.000179 (95% bootstrap interval -0.000149 to 0.000499). However, LightGBM AUC decreased to 0.7530 at Institution A and its calibration ECE10 reached 0.1129 at Institution C. Following correction of numeric-noise robustness tests, Random Forest and XGBoost had close nominal provisional technical means of 64.362 and 63.209, respectively; XGBoost ranked first under a 0.75 anchor-tolerance scale. Demographic-parity gaps were substantial, and expanded SHAP checks used 300 validation cases per model. Formal deployment rankings remained unavailable owing to incomplete independent governance and auditability evidence. BAIMRS provides a transparent descriptive comparison, not lending approval or regulatory certification.
Zitieren
APA
Anamika, Butail, A., & Rana, D. K. (2026). Beyond Accuracy: A Multi-Dimensional Explainability and Model-Risk Framework for AI-Based Credit Decisions in Banking. Computer and Decision Making: An International Journal, 3(6S), 2519-2550. https://doi.org/10.1922/comdem.v3i6s.19001
Vancouver
Anamika, Butail A, Rana DK. Beyond Accuracy: A Multi-Dimensional Explainability and Model-Risk Framework for AI-Based Credit Decisions in Banking. Computer and Decision Making: An International Journal. 2026;3(6S):2519-2550. doi:10.1922/comdem.v3i6s.19001
BibTeX
@article{Anamika2026,
author = {Anamika and Butail, Amit and Rana, Dr. Kritika},
title = {Beyond Accuracy: A Multi-Dimensional Explainability and Model-Risk Framework for AI-Based Credit Decisions in Banking},
journal = {Computer and Decision Making: An International Journal},
year = {2026},
volume = {3},
number = {6S},
pages = {2519--2550},
doi = {10.1922/comdem.v3i6s.19001}
}
EUVIMED