MLS-C01 Question #14: Real Exam Question with Answer & Explanation

Question

A Machine Learning team uses Amazon SageMaker to train an Apache MXNet handwritten digit classifier model using a research dataset. The team wants to receive a notification when the model is overfitting. Auditors want to view the Amazon SageMaker log activity report to ensure there are no unauthorized API calls. What should the Machine Learning team do to address the requirements with the least amount of code and fewest steps?

Options

• AImplement an AWS Lambda function to log Amazon SageMaker API calls to Amazon S3. Add
• BUse AWS CloudTrail to log Amazon SageMaker API calls to Amazon S3. Add code to push a
• CImplement an AWS Lambda function to log Amazon SageMaker API calls to AWS CloudTrail.
• DUse AWS CloudTrail to log Amazon SageMaker API calls to Amazon S3. Set up Amazon SNS to

Explanation

{"question_number": 5, "correct_answer": "B", "explanation": "AWS CloudTrail natively records all SageMaker API calls with zero custom code, writing them to an S3 bucket - this satisfies the auditors' requirement out of the box. To detect overfitting, SageMaker emits training metrics to Amazon CloudWatch; a CloudWatch Alarm can trigger an Amazon SNS notification when a metric (e.g., validation loss diverging from training loss) crosses a threshold. This combination - CloudTrail for audit logging, CloudWatch + SNS for alerting - requires minimal code and steps. Options using AWS Lambda (A, C) require writing and deploying custom functions. Moving logging to CloudTrail from Lambda (C) reverses the correct architecture.", "generated_by": "claude-sonnet", "llm_judge_score": 4}

No community discussion yet for this question.