DC-Guard: A Risk-Tiered Data-Centric Framework for Governing Dataset Shift in Credit-Risk Models — Empirical Validation on Fannie Mae Loans
Innovative Journal of Applied Science · 2025
DOI: 10.70844/ijas.2025.2.45 ↗Kurz gefasst
Fachartikel in der Zeitschrift Innovative Journal of Applied Science, 2025. Verfasst von Ashutosh Agarwal. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Machine-learning credit-default models degrade when production data diverge from training distributions. We introduce DC-Guard, a governance framework that maps Population-Stability-Index (PSI) and model-level drift (AUC, ECE) to Green / Amber / Red risk tiers and prescribes auditable actions (monitor, diagnose, retrain, restrict). We first ground the policy on the canonical UCI credit-card data set; we then validate it end-to-end on 2.1 million Fannie Mae single-family loans originated 2020–2023. On the live portfolio DC-Guard triggered exactly one red alert (Sep-2022) when PSI ≥ 0.2 and AUC dropped 0.058, prompting human-in-the-loop review and selective automation freeze until performance recovered. No false-positive retraining occurred. All code and data are publicly available.
Zitieren
APA
Agarwal, A. (2025). DC-Guard: A Risk-Tiered Data-Centric Framework for Governing Dataset Shift in Credit-Risk Models — Empirical Validation on Fannie Mae Loans. Innovative Journal of Applied Science. https://doi.org/10.70844/ijas.2025.2.45
Vancouver
Agarwal A. DC-Guard: A Risk-Tiered Data-Centric Framework for Governing Dataset Shift in Credit-Risk Models — Empirical Validation on Fannie Mae Loans. Innovative Journal of Applied Science. 2025. doi:10.70844/ijas.2025.2.45
BibTeX
@article{Agarwal2025,
author = {Agarwal, Ashutosh},
title = {DC-Guard: A Risk-Tiered Data-Centric Framework for Governing Dataset Shift in Credit-Risk Models — Empirical Validation on Fannie Mae Loans},
journal = {Innovative Journal of Applied Science},
year = {2025},
doi = {10.70844/ijas.2025.2.45}
}
EUVIMED