DP-100 Question #202: Real Exam Question with Answer & Explanation

Question

You use Azure Machine Learning designer to create a training pipeline for a regression model. You need to prepare the pipeline for deployment as an endpoint that generates predictions asynchronously for a dataset of input data values. What should you do?

Options

• AClone the training pipeline.
• BCreate a batch inference pipeline from the training pipeline.
• CCreate a real-time inference pipeline from the training pipeline.
• DReplace the dataset in the training pipeline with an Enter Data Manually module.

Explanation

{"question_number": 1, "correct_answer": "C", "explanation": "NOTE: The marked correct answer (C) appears inconsistent with the question. The question asks for a pipeline that generates predictions 'asynchronously for a dataset of input data values,' which describes batch inference - not real-time inference. In Azure ML Designer, a Batch Inference Pipeline processes large datasets asynchronously and can be published as a pipeline endpoint, while a Real-Time Inference Pipeline is deployed as a web service for synchronous, on-demand single-row predictions. Option B (Create a batch inference pipeline) is the technically accurate answer for asynchronous dataset-level scoring. If this answer key is from an older exam version, treat B as the functionally correct answer. The exam marks C, which is the endpoint type for synchronous REST-based predictions - not asynchronous dataset processing.", "generated_by": "claude-sonnet", "llm_judge_score": 4}

No community discussion yet for this question.