Free DP-100 Practice Test Questions and Answers (2026)

View Mode
Q: 1

HOTSPOT You load data from a notebook in an Azure Machine Learning workspace into a pandas dataframe named df. The data contains 10.000 patient records. Each record includes the Age property for the corresponding patient. You must identify the mean age value from the differentially private data generated by SmartNoise SDK. You need to complete the Python code that will generate the mean age value from the differentially private data. Which code segments should you use? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Microsoft DP 100 question

Your Answer
21 comments in the community discussion
5
Looks exactly like what you'd find in the official SDK docs or those practice exams, so I'd say Analysis() and epsilon.
5
Not everyone notices this, but if you're calculating a mean (not generating synthetic data), Analysis() is needed to define the DP workflow. For the privacy budget, epsilon is correct since that's what SmartNoise expects in privacy_usage. I think that's spot on, unless the
Q: 2

DRAG DROP You need to produce a visualization for the diagnostic test evaluation according to the data visualization requirements. Which three modules should you recommend be used in sequence? To answer, move the appropriate modules from the list of modules to the answer area and arrange them in the correct order. Microsoft DP 100 question

Drag & Drop
24 comments in the community discussion
5
Train Model → Score Model → Evaluate Model is what fits for diagnostic test evaluation. In Azure ML this sequence is standard for binary classification scenarios since Evaluate Model gives the ROC and confusion matrix visuals. If they wanted a recommender-specific pipeline, Evaluate Recommender would be last instead. P
5
Train Model → Score Model → Evaluate Model, that's the usual Azure ML order for test evaluation.
Q: 3

DRAG DROP You have a model with a large difference between the training and validation error values. You must create a new model and perform cross-validation. You need to identify a parameter set for the new model using Azure Machine Learning Studio. Which module you should use for each step? To answer, drag the appropriate modules to the correct steps. Each module may be used once or more than once, or not at all. You may need to drag the split bar between panes or scroll to view content. NOTE: Each correct selection is worth one point. Microsoft DP 100 question

Drag & Drop
26 comments in the community discussion
5
I think it should map like this: Two-Class Boosted Decision Tree for parameter scope, Partition and Sample for cross-validation settings, then Tune Model Hyperparameters handles both metric and training/evaluation. This fits how Azure ML Studio expects you to set up hyperparameter sweeps with cross-validation. Not 1
4
Yeah, this mapping makes sense: parameter scope to Two-Class Boosted Decision Tree, cross-validation settings is Partition and Sample, then both metric and train/evaluate/compare go with Tune Model Hyperparameters. Pretty sure that's the Azure ML workflow for hyperparameter search. Seen similar setups in labs, but c
Q: 4
You use the designer to create a training pipeline for a classification model. The pipeline uses a dataset that includes the features and labels required for model training. You create a real-time inference pipeline from the training pipeline. You observe that the schema for the generated web service input is based on the dataset and includes the label column that the model predicts. Client applications that use the service must not be required to submit this value. You need to modify the inference pipeline to meet the requirement. What should you do?
Options
17 comments in the community discussion
1
A , real exam/training always pushes Select Columns for removing label column cleanly from inference schema. So A.
1
C/D? Official guide and lab exercises both cover when to use clusters vs AKS for batch.
Q: 5
You plan to build a team data science environment. Data for training models in machine learning pipelines will be over 20 GB in size. You have the following requirements: Models must be built using Caffe2 or Chainer frameworks. Data scientists must be able to use a data science environment to build the machine learning pipelines and train models on their personal devices in both connected and disconnected network environments. Personal devices must support updating machine learning pipelines when connected to a network. You need to select a data science environment. Which environment should you use?
Options
25 comments in the community discussion
6
Option A saw a similar question in practice and Studio misses support for Caffe2/Chainer.
4
B. training jobs need AmlCompute not AKS if it's only set up for inference. I've seen similar wording on other practice sets, pretty sure this is what they're testing for. Let me know if you disagree!
Q: 6

DRAG DROP You manage an Azure Al Foundry project. You deploy a large language model from the model catalog. You need to manually evaluate the model, collect the statistics, and be able to review the results later. Microsoft DP 100 question

Drag & Drop
22 comments in the community discussion
6
Import data in CSV format, then thumbs up or down, then save evaluation results. That’s the sequence for manual eval here.
4
Import data in CSV format → thumbs up/down ratings → save the results. Manual process, not auto-generate here.
Q: 7

DRAG DROP You are producing a multiple linear regression model in Azure Machine Learning Studio. Several independent variables are highly correlated. You need to select appropriate methods for conducting effective feature engineering on all the data. Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. Microsoft DP 100 question

Drag & Drop
30 comments in the community discussion
7
Option C Clear question, seen similar in practice sets too.
5
Nah, it's not "Compute linear correlation" first. Gotta clear duplicates before checking correlation, or you'll get misleading results. Some might pick "Test hypothesis using t-Test" but that's not for feature selection here.
Q: 8

HOTSPOT You are evaluating a Python NumPy array that contains six data points defined as follows: data = [10, 20, 30, 40, 50, 60] You must generate the following output by using the k-fold algorithm implantation in the Python Scikit-learn machine learning library: train: [10 40 50 60], test: [20 30] train: [20 30 40 60], test: [10 50] train: [10 20 30 50], test: [40 60] You need to implement a cross-validation to generate the output. How should you complete the code segment? To answer, select the appropriate code segment in the dialog box in the answer area. NOTE: Each correct selection is worth one point. Microsoft DP 100 question

Your Answer
31 comments in the community discussion
8
Option B SAS token
6
Looks like the right setup is KFold, 3, data. You need n_splits=3 because there are three distinct train/test splits in the output, not just two samples per test set. Pretty sure that's how sklearn's KFold works, but open to disagreement.
Q: 9

HOTSPOT You manage an Azure Machine Learning workspace named workspace1. You must register an Azure Blob storage datastore in workspace1 by using an access key. You develop Python SDK v2 code to import all modules required to register the datastore. You need to complete the Python SDK v2 code to define the datastore. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Microsoft DP 100 question

Your Answer
28 comments in the community discussion
6
container_name and wasbs
6
container_name and wasbs are the right picks here. For AzureBlobDatastore in Python SDK v2, you need container_name to tell it which blob container to use, and wasbs as the protocol works for classic Azure Blob Storage. filesystem and abfss are only for Data Lake Gen2 setups. I think this l
Q: 10
You use Azure Machine Learning studio to analyze an mltable data asset containing a decimal column named column1. You need to verify that the column1 values are normally distributed. Which statistic should you use?
Options
29 comments in the community discussion
6
C . Profile in Azure ML Studio gives you distribution charts and extra stats (like skewness) so you can actually see if it's normal, not just the average. Pretty sure that's what you'd use for this kind of check but open to hearing other takes.
6
Isn't "Profile" (option C) what actually gives you the distribution overview in Azure ML, not just a single stat like mean?
Q: 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 create a model to forecast weather conditions based on historical data. You need to create a pipeline that runs a processing script to load data from a datastore and pass the processed data to a machine learning model training script. Solution: Run the following code: Microsoft DP 100 question Does the solution meet the goal?

Options
5 comments in the community discussion
6
Option A This matches what I saw in the official MS docs and some exam practice, where ScriptRunConfig manages both your scripts and data, and setting the environment with from_conda_spec handles the packages.
5
A . B is tempting but the conda env and sourcedirectory bits are what the exam wants.
Q: 12

DRAG DROP You need to correct the model fit issue. Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. Microsoft DP 100 question

Drag & Drop
6 comments in the community discussion
1
Ordinal Regression, Two-Class Averaged Perception, decrease memory size for L-BFGS.I picked these because I thought the issue was with a classification model misfit, so started with Ordinal Regression and then added Two-Class Averaged Perception for more flexibility, plus tweaking memory settings for L-BFGS to
D
Q: 13
An organization creates and deploys a multi-class image classification deep learning model that uses a set of labeled photographs. The software engineering team reports there is a heavy inferencing load for the prediction web services during the summer. The production web service for the model fails to meet demand despite having a fully-utilized compute cluster where the web service is deployed. You need to improve performance of the image classification web service with minimal downtime and minimal administrative effort. What should you advise the IT Operations team to do?
Options
7 comments in the community discussion
8
Not sure but pretty sure it's Policy/Outcome Metrics for real-world impact, and Counterfactuals for minimal change examples. Can someone confirm?
5
D . Scaling out by adding more nodes is usually quickest with less admin overhead, and no need to redeploy or update DNS. Makes sense for handling spikes like this.
Q: 14
You manage an Azure Machine Learning workspace named projl You plan to use assets defined in projl to create a pipeline in the Machine Learning studio designer You need to set the Registry name filter to display only the list of assets defined in projl. What should you set the Registry name filter to?
Options
11 comments in the community discussion
3
Microsoft really likes to overcomplicate the steps for compute attachment. Sequence would change if they wanted existing Synapse resources or if you had to create new ones from scratch. Clarification on that would flip the order!
2
Option B is the one. The filter should be set to "workspace" to only show assets local to proj1, not the other registry names. Pretty sure this matches what you see in the Studio docs and practice labs.
Q: 15

DRAG DROP You are managing an Azure Machine Learning workspace. You must tune a hyperparameter for a neural network model. The learning rate must be a continuous hyperparameter between 0.001 and 0.1. The batch size can be 32.64. or 128. You need to select the appropriate search space for each parameter. Which search space should you use? To answer, move the appropriate search spaces to the correct hyperparameters. You may use each search space 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. Microsoft DP 100 question

Drag & Drop
7 comments in the community discussion
3
Learning rate -> Uniform, Batch size -> Choice. Uniform is for continuous ranges (like 0.001 to 0.1), while Choice works for picking from set values like 32, 64, or 128. Normal and QNormal are trap options here since the question doesn't ask for probabilistic sampling. Pretty sure this matches Azure ML docs, corr
2
Nah, I’m pretty sure the right order is: set up local environment, debug the scoring script locally, then fix and retest before pushing to Azure. A lot of folks get trapped trying to redeploy without a local test, which won't help if it's a script bug. If someone thinks dependencies should come first, let me know.
Q: 16

HOTSPOT You plan to use Hyperdrive to optimize the hyperparameters selected when training a model. You create the following code to define options for the hyperparameter experiment Microsoft DP 100 question Microsoft DP 100 question For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Microsoft DP 100 question

Your Answer
9 comments in the community discussion
4
Update Import Data → Run pipeline → Register dataset → Deploy model. Saw a similar question before and this order avoids the trap of registering before running the pipeline. Makes sense since you want new data first, right? Correct me if I missed something.
1
Update Import Data → Run pipeline → Register dataset → Deploy model
Q: 17

HOTSPOT Your Azure Machine Learning workspace has a dataset named real_estate_dat a. A sample of the data in the dataset follows. Microsoft DP 100 question You want to use automated machine learning to find the best regression model for predicting the price column. You need to configure an automated machine learning experiment using the Azure Machine Learning SDK. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Microsoft DP 100 question

Your Answer
7 comments in the community discussion
5
Looks like the order should be: training_data, validation_data, label_column_name. That's how you set it up in Azure ML SDK for a regression job. Pretty confident here but open if anyone has seen different lately.
4
Yep, that's how AzureML SDK wants it: training_data, validation_data, label_column_name.
Q: 18

HOTSPOT You must use in Azure Data Science Virtual Machine (DSVM) as a compute target. You need to attach an existing DSVM to the workspace by using the Azure Machine Learning SDK for Python. How should you complete the following code segment? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Microsoft DP 100 question

Your Answer
7 comments in the community discussion
2
attach_configuration for the first box, attach for the second. You use attach_configuration to set up how the DSVM connects, then attach to register it with your workspace. Pretty sure this is standard in AML SDK when adding existing compute. Let me know if anyone found a different method.
1
Actually, I think create_configuration for Box 1 and attach for Box 2 seems right. In some SDK patterns, you use create_configuration before registering existing compute. But this might mix up with AMLCompute, so not 100% confident. Anyone else run into this trap?
Q: 19
You are building a recurrent neural network to perform a binary classification. You review the training loss, validation loss, training accuracy, and validation accuracy for each training epoch. You need to analyze model performance. Which observation indicates that the classification model is over fitted?
Options
4 comments in the community discussion
6
Filter Based Feature Selection -> Build Counting Transform -> Test hypothesis with t-Test. This sequence deals with multicollinearity then adds useful categorical features, before statistically validating them. Pretty clear order for feature engineering steps in regression, seen similar in practice tests. Nice
Probably C here. I've seen similar questions on practice sets, and when training loss goes down but validation loss goes up, that's a textbook sign of overfitting. Anyone else see this pattern come up?
Q: 20

HOTSPOT You have an Azure Machine Learning workspace. You plan to use Azure Machine Learning Python SDK v2 to define a pipeline component that trains an image classification model. The execution logic of the component is contained in the train() function in the file named modeljrain.py. You write code to import all required libraries and store it as train_component.py in the same folder that contains model_train.py. You need to complete the remaining code in train_component.py. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Microsoft DP 100 question

Your Answer
8 comments in the community discussion
4
COMMAND_COMPONENT, MODEL_TRAIN
3
Select model feature, then choose the binary/regression model, finally pick the metric to measure. Saw similar order come up on practice tests.
Question 1 of 20

What's covered in this practice questions set

2: Run experiments and train models · 15 questions

📖 About this Domain

This domain covers the execution of model training processes within the Azure Machine Learning workspace. It focuses on creating and running script-based experiments, logging metrics, and managing training jobs on various compute targets.

🎓 What You Will Learn

  • You will learn to create and run script-based experiments using the Azure Machine Learning SDK and CLI v2.
  • You will learn to consume data from datastores and data assets for model training jobs.
  • You will learn to implement model training using frameworks like Scikit-learn and log metrics with MLflow for run tracking.
  • You will learn to configure and use compute targets, such as compute clusters, for scalable training jobs.

🛠️ Skills You Will Build

  • You will build the skill to write Python scripts that connect to an Azure ML workspace, access data, and train a machine learning model.
  • You will build the skill to configure and submit command jobs using YAML definitions for reproducible and scalable training runs.
  • You will build the skill to integrate MLflow for autologging or custom logging of parameters, metrics, and artifacts during an experiment run.
  • You will build the skill to analyze experiment run history, compare metrics, and retrieve the best model from a completed job.

💡 Top Tips to Prepare

  • Master the structure of YAML files for defining command jobs, including inputs, code, environment, and compute specifications.
  • Practice using both the Azure ML SDK v2 and CLI v2 to submit and manage training jobs, as the exam covers both.
  • Understand the different ways to log metrics, specifically the distinction between logging single values versus logging artifacts like charts.
  • Focus on how to retrieve a registered model from a job run and understand the relationship between a job, its outputs, and the model registry.

3: Deploy and operationalize machine learning solutions · 3 questions

📖 About this Domain

This domain covers the operationalization of machine learning models using Azure Machine Learning. You will focus on deploying models as real-time and batch endpoints, and automating workflows with pipelines for continuous integration and delivery (CI/CD). It is the core of MLOps practices within the Azure ecosystem.

🎓 What You Will Learn

  • Deploy trained models as real-time endpoints on compute targets like Azure Container Instance (ACI) or Azure Kubernetes Service (AKS) for immediate inference.
  • Implement batch inference pipelines to process large volumes of data asynchronously using batch endpoints.
  • Configure data drift and model performance monitoring to maintain model quality and detect degradation in production.
  • Automate the end-to-end ML lifecycle by creating, publishing, and scheduling Azure Machine Learning pipelines using components.

🛠️ Skills You Will Build

  • Ability to package models with scoring scripts and environment configurations for containerized deployment.
  • Proficiency in creating, managing, and troubleshooting both real-time and batch inference endpoints via the SDK, CLI v2, and studio.
  • Competence in building and parameterizing reusable ML pipelines for training and retraining workflows.
  • Capability to set up data drift monitors on datasets and interpret results to trigger automated actions like retraining.

💡 Top Tips to Prepare

  • Master the differences between ACI for dev/test deployments and AKS for production-scale, high-availability endpoints.
  • Practice defining endpoints, deployments, and pipeline components using YAML configuration files for the CLI v2.
  • Gain hands-on experience with the Azure CLI v2 for managing all MLOps assets, as it is a key focus of the exam.
  • Understand the concepts of a baseline dataset versus a target dataset when configuring a data drift monitor.

4: Implement responsible machine learning · 1 questions

📖 About this Domain

This domain covers the operationalization of ethical AI principles using Azure Machine Learning. It focuses on implementing tools and techniques to ensure fairness, interpretability, and privacy in machine learning models. You will work with the Responsible AI dashboard to assess and mitigate potential harms.

🎓 What You Will Learn

  • You will learn to use the Responsible AI dashboard to evaluate models for fairness and identify disparities across demographic groups.
  • You will learn to implement model explainability techniques, such as SHAP, to interpret model predictions and understand feature importance.
  • You will learn to analyze model errors and identify causal relationships to improve model reliability and robustness.
  • You will learn the core concepts of differential privacy and how it can be applied to protect sensitive user data during the training process.

🛠️ Skills You Will Build

  • You will build the skill to configure and interpret Responsible AI scorecards for a holistic assessment of model performance and fairness.
  • You will build the skill to generate both global and local explanations for models to debug and validate their behavior.
  • You will build the skill to apply fairness mitigation algorithms from the Fairlearn toolkit to retrain models and reduce bias.
  • You will build the skill to identify data drift and other failure modes in production models to ensure ongoing reliability.

💡 Top Tips to Prepare

  • Focus on the components of the Responsible AI dashboard, including error analysis, model explainability, and fairness assessment.
  • Practice interpreting SHAP values and other explainer outputs to understand a model's decision-making process.
  • Understand the different fairness metrics, such as demographic parity and equalized odds, and when to apply them.
  • Review how to configure a pipeline job in Azure ML that includes a component for generating a Responsible AI dashboard.

1: Set up an Azure Machine Learning workspace · 1 questions

📖 About this Domain

This domain covers the provisioning and configuration of the Azure Machine Learning workspace, the foundational resource for machine learning operations. The workspace is the top-level resource that centralizes all ML artifacts and orchestrates dependent Azure resources.

🎓 What You Will Learn

  • Provision an Azure Machine Learning workspace using the Azure portal, Azure CLI, and Python SDK.
  • Identify the dependent Azure resources created with a workspace, including Storage Account, Key Vault, Application Insights, and Container Registry.
  • Manage workspace access and permissions using Azure Role-Based Access Control (RBAC) for different user roles.
  • Navigate the Azure Machine Learning studio to locate and manage workspace assets and properties.

🛠️ Skills You Will Build

  • Deploying and configuring the core Azure Machine Learning environment required for any data science project.
  • Implementing security controls by assigning built-in RBAC roles like Owner, Contributor, and Reader to users and service principals.
  • Managing the lifecycle of a workspace, including understanding its properties and associated resource dependencies.
  • Utilizing the Azure Machine Learning studio as the primary user interface for interacting with workspace assets.

💡 Top Tips to Prepare

  • Practice creating a workspace using all three methods: Azure portal, Python SDK (Workspace.create), and Azure CLI (az ml workspace create).
  • Memorize the four Azure resources automatically provisioned with a workspace and their specific functions.
  • Understand the distinction between the Basic and Enterprise workspace editions and their feature differences.
  • Know the specific permissions granted by the standard RBAC roles (Owner, Contributor, Reader) within the context of a workspace.

Premium Access Includes

  • ✓Quiz Simulator
  • ✓Exam Mode
  • ✓Progress Tracking
  • ✓Question Saving
  • ✓Flash Cards
  • ✓Drag & Drops
  • ✓3 Months Access
  • ✓PDF Downloads
Get Premium Access
Scroll to Top

FLASH OFFER

Days
Hours
Minutes
Seconds

avail 10% DISCOUNT on YOUR PURCHASE

  • USE THE CODE GIVEN BELOW ON YOUR CHECKOUT
DISCOUNT10