AmirhosseinHonardoust/Underwriting-Decision-Safety-Lab
A decision-safety lab for loan approval: trains a baseline classifier, calibrates probabilities (ECE/Brier), sweeps confidence thresholds to build a coverage, quality frontier and outputs a defensible abstention policy (auto-decide vs review). Includes a Streamlit dashboard for report cards, triage UI, and data quality checks.
This tool helps credit risk managers and loan officers establish a safe, defensible process for loan approvals. It takes your loan application data and a trained approval model, then helps you understand the true confidence of its predictions. The output is a recommended policy that categorizes applications into auto-approve, auto-reject, or manual review, along with an interactive dashboard for analysis and triage.
Use this if you need to turn raw loan approval model scores into actionable, transparent, and auditable decisions that protect against risky auto-approvals or unfair rejections.
Not ideal if you need a production-ready, highly scalable loan origination system with real-time API integrations, as this is designed as a decision-safety lab and prototype.
Stars
11
Forks
—
Language
Python
License
MIT
Category
Last pushed
Feb 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmirhosseinHonardoust/Underwriting-Decision-Safety-Lab"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xRiskLab/xBooster
Explainable Boosted Scoring with Python: turning XGBoost, LightGBM, and CatBoost into...
ing-bank/skorecard
scikit-learn compatible tools for building credit risk acceptance models
minerva-ml/open-solution-home-credit
Open solution to the Home Credit Default Risk challenge :house_with_garden:
semasuka/Credit-card-approval-prediction-classification
Credit risk analysis for credit card applicants
ParthS007/Loan-Approval-Prediction
Loan Application Data Analysis