naenumtou/ifrs9
The full scope of IFRS 9 Impairment models including PD, LGD and EAD are provided. It also covers ECL, which is the combination of those three parameters as well as staging criteria.
Implements a three-stage impairment model with automated workflow from raw loan data through PD/LGD/EAD component modeling, incorporating macroeconomic forecasts and discounting via EIR to produce stage-allocated provisions. Built in Python with Google Colab compatibility, it enables banks to segment credit risk across portfolio characteristics and transition loans between stages based on significant credit risk increases. The framework generates 12-month and lifetime ECL forecasts suitable for downstream integration into accounting systems.
109 stars.
Stars
109
Forks
44
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/naenumtou/ifrs9"
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