CreditRisk Intelligence — AI-Powered Credit Risk Infrastructure for Fintechs
-
Updated
Jun 12, 2026 - Python
CreditRisk Intelligence — AI-Powered Credit Risk Infrastructure for Fintechs
VaR/CVaR investment portfolio risk modeling with backtesting
Pipeline de credit risk end-to-end: PD logística, Monte Carlo vectorizado, métricas Basel III (EL, VaR, Expected Shortfall) y stress testing. Python · NumPy · pandas · statsmodels
Basel Vasicek credit risk stress testing model with TTC PD estimation, stressed PD mapping, and facility-level Unexpected Loss (UL) analysis.
An object-oriented, Walk-Forward quantitative risk engine estimating VaR and Expected Shortfall using a Student-t Copula and GJR-GARCH margins
Monitors SEC/CFTC/FCA/Basel/Federal Reserve publications and generates structured regulatory impact assessments
Eight VaR/ES models for a $10m multi-asset book, validated over 4,611 trading days with Kupiec, Christoffersen, Basel traffic-light and Acerbi-Szekely tests.
Local tools for querying and visualizing changes in the Basel-Stadt nature inventory.
Bank-grade credit-risk platform — calibrated PD scorecard + ML challenger, LGD/EAD -> Expected Loss, OOT validation, SHAP reason codes, fairness & drift. Basel/IRB on Freddie Mac data.
IFRS 9 ECL engine on 2.26M Lending Club loans: PD scorecard, LGD/EAD models, Basel IRB capital, 3-stage ECL with macro scenarios and full model validation.
Add a description, image, and links to the basel topic page so that developers can more easily learn about it.
To associate your repository with the basel topic, visit your repo's landing page and select "manage topics."