DP-100 Question #422: Real Exam Question with Answer & Explanation

Question

You are using Azure Machine Learning to monitor a trained and deployed model. You implement Event Grid to respond to Azure Machine Learning events. Model performance has degraded due to model input data changes. You need to trigger a remediation ML pipeline based on an Azure Machine Learning event. Which event should you use?

Options

• ARunStatusChanged
• BRunCompleted
• CDatasetDriftDetected
• DModelDeployed

Explanation

{"question_number": 3, "correct_answer": "C", "explanation": "The DatasetDriftDetected event is the correct choice because it is specifically fired when Azure Machine Learning's data drift monitoring service detects that the statistical properties of the model's input data have shifted from the baseline (training data). This is exactly the scenario described - model performance degraded due to model input data changes (data drift). RunStatusChanged and RunCompleted relate to the lifecycle of training or pipeline runs, not data quality. ModelDeployed fires when a model is newly deployed, not when performance degrades. Only DatasetDriftDetected is designed to signal that input data distribution has changed, making it the appropriate trigger for a remediation pipeline.", "generated_by": "claude-sonnet", "llm_judge_score": 4}

No community discussion yet for this question.