AML Risk Assessment & Management 2

Question 1

Which technique is most appropriate for quantifying uncertainty in a neural network's predictions to support risk-aware decision making?

Accepted Answer

Dropout at inference time (MC Dropout)

Answer

MC Dropout approximates Bayesian inference by running multiple stochastic forward passes at test time, yielding a distribution over predictions that reflects model uncertainty.

Question 2

In a high-stakes ML deployment, what does 'model risk' primarily refer to?

Accepted Answer

Adverse outcomes arising from incorrect or misused model outputs

Answer

Model risk encompasses the potential for financial loss, regulatory penalty, or harm caused by errors in model development, implementation, or inappropriate use of predictions.

Question 3

A credit scoring model shows strong performance on historical data but degrades rapidly after deployment. Which risk category best describes this phenomenon?

Accepted Answer

Data drift risk

Answer

Data drift occurs when the statistical properties of input features change over time post-deployment, causing models trained on historical distributions to underperform.

Question 4

When assessing risks of an ML model in a regulated industry, which document type formally captures identified risks and corresponding mitigations?

Accepted Answer

A model risk register

Answer

A model risk register systematically catalogs identified risks, their likelihood, potential impact, and the mitigations or controls applied to each.

Question 5

What is the primary purpose of stress-testing an ML model during risk assessment?

Accepted Answer

To evaluate model behavior under extreme or adversarial input conditions

Answer

Stress testing exposes the model to edge cases, outliers, and adversarial inputs to reveal failure modes that may not appear in standard evaluation.

(AML) Advanced Machine Learning Certification Practice Test

(AML) Advanced Machine Learning Certification Practice Test

AML Risk Assessment & Management 2