Large Bank Examination Workshop February 2026

Model Stress and Stability Tests • Sensitivity analysis checks the impact of small changes in inputs and parameter values on model outputs.

• Unexpectedly large changes in outputs in response to small changes in inputs may indicate an unstable model.

• Simultaneous variation of multiple inputs may provide evidence of unexpected interactions. Can we show how these arise in the model, and can we explain them intuitively? • Stress tests should evaluate the model over a wide range of inputs and parameter values, including extreme values, to verify that the model is robust.

103

Applying Stress Test Results • Model stress tests establish boundaries for model performance.

• What is the acceptable range of inputs for the model?

• Under what conditions or for what parameter values or inputs may the model become unstable or inaccurate?

• What should we do if testing reveals that the model may be inaccurate or unstable in some circumstances?

104

52

© Global Financial Markets Institute Inc.