This is the free Microsoft DP-100 practice question bank —
240 of 477 total questions, each with a full explanation, free to
read with no signup required. Updated 2026-04-24.
Every answer is verified against official Microsoft documentation —
see our methodology.
Question 1
You are implementing hyperparameter tuning by using Bayesian sampling for an Azure ML Python SDK v2-based model training from a notebook. The notebook is in an Azure Machine Learning workspace. The notebook uses a training script that runs on a compute cluster with 20 nodes.
The code implements Bandit termination policy with slack_factor set to 0.2 and a sweep job with max_concurrent_trials set to 10.
You must increase effectiveness of the tuning process by improving sampling convergence.
You need to select which sampling convergence to use.
What should you select?
A. Set the value of max_concurrent_trials to 20.
B. Set the value of slack_factor of early_termination policy to 0.1.
C. Set the value of slack_factor of early_termination policy to 0.9.
D. Set the value of max_concurrent_trials to 4.
Show Answer
Correct Answer: D
Explanation: Bayesian sampling in Azure ML is sequential and relies on results from completed trials to guide the next hyperparameter choices. With a high max_concurrent_trials value, many runs start simultaneously and cannot benefit from each other’s outcomes, reducing convergence and behaving more like random sampling. Lowering max_concurrent_trials (for example, to 4) allows more completed results to inform subsequent trials, improving Bayesian sampling convergence. Changing the slack_factor affects early termination aggressiveness, not sampling convergence.
Question 2
DRAG DROP
-
You manage an Azure Machine Learning workspace that has an Azure Machine Learning datastore.
Data must be loaded from the following sources:
• a credential-less Azure Blob Storage
• an Azure Data Lake Storage (ADLS) Gen 2 which is not a credential-less datastore
You need to define the authentication mechanisms to access data in the Azure Machine Learning datastore.
Which data access mechanism should you use? To answer, move the appropriate data access mechanisms to the correct storage types. You may use each data access mechanism once, more than once, or not at all. You may need to move the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Azure Blob Storage
Shared access signature (SAS) token
Azure Data Lake Storage (ADLS) Gen 2
Service principal
Explanation: Credential-less Blob Storage is accessed using a SAS token, which provides scoped, time-bound access without permanent credentials. ADLS Gen2 requires Azure AD–based authentication; a service principal is the standard supported mechanism for Azure Machine Learning datastores.
Question 3
You are using the Azure Machine Learning SDK to run a training experiment that trains a classification model and calculates its accuracy metric.
The model will be retrained each month as new data is available.
You must register the model for use in a batch inference pipeline.
You need to register the model by using mlflow and ensure that the models created by subsequent retraining experiments are registered only if their accuracy is higher than the currently registered model.
What should you do?
A. Register a metric named accuracy with the accuracy metric as a value when registering the model, and only register subsequent models if their accuracy is higher than the accuracy tag value of the currently registered model.
B. Specify the model framework version when registering the model, and only register subsequent models if this value is higher.
C. Register the model with the same name each time regardless of accuracy, and always use the latest version of the model in the batch inferencing pipeline.
D. Specify a different name for the model each time you register it.
Show Answer
Correct Answer: A
Explanation: In Azure ML with MLflow, you control conditional registration logic in your training code. You log the model’s evaluation metric (for example, accuracy) using mlflow.log_metric and/or store it as a model tag or run metric. Before registering a new model version, you compare its accuracy against the accuracy associated with the currently registered model version, and only register if it is higher. Model framework versioning, model name changes, or always using the latest version do not enforce quality-based promotion.
Question 5
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You have an Azure Machine Learning workspace.
You plan to tune model hyperparameters by using a sweep job.
You need to find a sampling method that supports early termination of low-performance jobs and continuous hyperparameters.
Solution: Use the Sobol sampling method over the hyperparameter space.
Does the solution meet the goal?
A. Yes
B. No
Show Answer
Correct Answer: A
Explanation: The requirement is a sampling method that supports both continuous hyperparameters and early termination of low-performing runs. In Azure Machine Learning sweep jobs, Sobol sampling supports continuous parameters, and early termination policies (such as Bandit or Median Stopping) are applied independently of the sampling method. Early termination is not supported only with Grid sampling. Therefore, using Sobol sampling meets both stated goals.
Question 6
You manage an Azure Machine Learning workspace. You use Azure Machine Learning Python SDK v2 to configure a trigger to schedule a pipeline job.
You need to create a time-based schedule with recurrence pattern.
Which two properties must you use to successfully configure the trigger? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
A. interval
B. start_time
C. schedule
D. time_zone
E. frequency
Show Answer
Correct Answer: A, E
Explanation: In Azure Machine Learning Python SDK v2, a time-based schedule with a recurrence pattern is defined using a RecurrenceTrigger. The recurrence pattern itself is configured with the properties `frequency` (such as minute, hour, day, week) and `interval` (how often the frequency repeats). Other properties like `start_time` or `time_zone` are optional, and `schedule` is not a recurrence configuration property. Therefore, `interval` and `frequency` are required to successfully define the recurrence.
Question 7
DRAG DROP
-
You are designing an Azure Machine Learning solution.
The model must be trained by using automated machine learning. The compute must be a shared resource with users in the Azure Machine Learning workspace. After you train the model, it must be deployed for batch scoring on a serverless compute.
You need to select the appropriate computation options for the solution.
Which compute options should you select for training and deployment? To answer, move the appropriate compute options to the correct project activities. You may use each compute option once, more than once, or not at all. You may need to move the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Train the model → Azure Machine Learning compute cluster
Deploy the model → Azure Machine Learning serverless compute
Explanation: Automated ML training requires a shared, scalable compute resource, which is provided by an Azure Machine Learning compute cluster. Batch scoring on a serverless compute is supported by Azure Machine Learning serverless compute, which removes infrastructure management for deployments.
Question 8
You manage an Azure Machine Learning workspace.
You experiment with an MLflow model that trains interactively by using a notebook in the workspace.
You need to log dictionary type artifacts of the experiments in Azure Machine Learning by using MLflow.
Which syntax should you use?
A. mlflow.log_artifact(my_dict)
B. mlflow.log_metric("my_metric", my_dict)
C. mlflow.log_metrics(my_dict)
D. mlflow.log_artifacts(my_dict)
Show Answer
Correct Answer: C
Explanation: In MLflow, dictionaries are logged using the bulk logging helpers. `mlflow.log_metrics()` accepts a dictionary of key–value pairs and logs each entry as a metric. `log_artifact(s)` are for files or directories, and `log_metric` logs only a single scalar value, not a dictionary.
Question 9
DRAG DROP
-
You are designing an Azure Machine Learning solution by using the Python SDK v2.
You must train and deploy the solution by using a compute target. The compute target must meet the following requirements:
• Enable the use of on-premises compute resources.
• Support autoscaling.
You need to configure a compute target for training and inference.
Which compute targets should you configure?
To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Explanation: Azure Machine Learning Kubernetes (AKS or Arc-enabled Kubernetes) supports autoscaling and can be connected to on‑premises resources via Azure Arc. Local compute does not support autoscaling, and Apache Spark pools are cloud-only and not suitable for on‑premises inference.
Question 10
HOTSPOT
-
You have an Azure subscription that contains a resource group named rg-ml.
You plan to create an Azure Machine Learning workspace named workspace1 in rg-ml by using Azure Machine Learning Python SDK v2.
You need to ensure workspace is configured to prevent the collection of potentially sensitive data by Microsoft diagnostics.
How should you complete the provided code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: from azure.ai.ml.entities import Workspace
hbi_workspace = False
Explanation: In Azure ML SDK v2, Workspace is defined in azure.ai.ml.entities. Setting hbi_workspace=False disables High Business Impact mode, which prevents Microsoft from collecting potentially sensitive diagnostic data.
Question 11
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You have an Azure Machine Learning workspace that includes an AmlCompute cluster and a batch endpoint.
You clone a repository that contains an MLflow model to your local computer.
You need to ensure that you can deploy the model to the batch endpoint.
Solution: Create a datastore in the workspace.
Does the solution meet the goal?
A. Yes
B. No
Show Answer
Correct Answer: B
Explanation: Creating a datastore in the Azure Machine Learning workspace is not required to deploy an existing MLflow model to a batch endpoint. Batch deployments can reference models directly from the model registry or local artifacts when registering the model. While datastores are useful for data access, they are not a prerequisite for deploying an MLflow model to a batch endpoint, so the solution does not meet the stated goal.
$19
Get all 477 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.
