credit-risk-calculator

To calculate probability of default (PD) and identify risk drivers, the skill processes borrower financial features to generate baseline PD scores and uses SHAP analysis to pinpoint the specific metrics influencing the rating.

You can stress test credit risk by running what-if scenarios to simulate revenue drops, interest rate hikes, or leverage changes, allowing you to compare how these adverse conditions impact borrower risk ratings.

Yes, you can use pandas and numpy for financial modeling and stress testing, as the skill explicitly requires both libraries to execute data manipulation and model inference for credit risk calculations.

The best way to compare credit risk scenarios is to run multiple stress testing simulations on your portfolio, evaluating how varying revenue drops and interest rate hikes alter default probabilities across borrowers.

SHAP analysis explains credit risk by evaluating the specific financial drivers contributing to a borrower's PD score, breaking down how individual features influence the final default probability calculation.

You do not need external model inference scripts, as the skill includes internal scripts to perform sensitivity analysis on credit metrics, relying solely on numpy and pandas for execution.