What is the role of explainability in CPMAI and name one technique to achieve it.

• A. To improve model accuracy beyond all else.
• B. To help stakeholders understand model decisions; techniques include SHAP values or LIME.
• C. To minimize data requirements for training.
• D. To increase sampling speed in inference.

Answer: (B)

Explainability in CPMAI is about making model decisions understandable to stakeholders. This helps with trust, governance, risk management, and accountability by providing clear reasons for each prediction. A concrete technique to achieve this is SHAP values, which quantify how much each input feature contributes to a specific prediction, yielding local explanations that reflect the model's actual behavior. Not focused on simply boosting accuracy, reducing data needs, or speeding up inference, explainability centers on presenting understandable rationale behind decisions, with SHAP as a practical method.