Exam DP-100: Designing and Implementing a Data Science Solution on Azure

Study guide for Exam DP-100: Designing

and Implementing a Data Science Solution
on Azure
Purpose of this document
This study guide should help you understand what to expect on the exam and includes a summary of
the topics the exam might cover and links to additional resources. The information and materials in this
document should help you focus your studies as you prepare for the exam.

Useful links Description

Review the skills measured This list represents the skills measured AFTER the date provided.
as of March 14, 2023 Study this list if you plan to take the exam AFTER that date.

Review the skills measured Study this list of skills if you take your exam PRIOR to the date
prior to March 14, 2023 provided.

Change log You can go directly to the change log if you want to see the
changes that will be made on the date provided.

How to earn the Some certifications only require passing one exam, while others
certification require passing multiple exams.

Certification renewal Microsoft associate, expert, and specialty certifications expire

annually. You can renew by passing a free online assessment on
Microsoft Learn.

Your Microsoft Learn Connecting your certification profile to Learn allows you to schedule
profile and renew exams and share and print certificates.

Passing score A score of 700 or greater is required to pass.

Exam sandbox You can explore the exam environment by visiting our exam
sandbox.

1
 Exam DP-100: Designing and Implementing a Data Science Solution on Azure

Useful links Description

Request accommodations If you use assistive devices, require extra time, or need modification
to any part of the exam experience, you can request an
accommodation.

Take a practice test Are you ready to take the exam or do you need to study a bit more?

Updates to the exam

Our exams are updated periodically to reflect skills that are required to perform a role. We have
included two versions of the Skills Measured objectives depending on when you are taking the exam.
We always update the English language version of the exam first. Some exams are localized into other
languages, and those are updated approximately eight weeks after the English version is updated.
Other available languages are listed in the Schedule Exam section of the Exam Details webpage. If the
exam isn't available in your preferred language, you can request an additional 30 minutes to complete
the exam.

Note
The bullets that follow each of the skills measured are intended to illustrate how we are assessing that
skill. Related topics may be covered in the exam.

Note
Most questions cover features that are general availability (GA). The exam may contain questions on
Preview features if those features are commonly used.

Skills measured as of March 14, 2023

Audience profile
Candidates for the Azure Data Scientist Associate certification should have subject matter expertise in
applying data science and machine learning to implement and run machine learning workloads on
Azure.
Responsibilities for this role include designing and creating a suitable working environment for data
science workloads; exploring data; training machine learning models; implementing pipelines; running
jobs to prepare for production; and managing, deploying, and monitoring scalable machine learning
solutions.
A candidate for this certification should have knowledge and experience in data science by using Azure
Machine Learning and MLflow.
• Design and prepare a machine learning solution (20–25%)
• Explore data and train models (35–40%)

2
 Exam DP-100: Designing and Implementing a Data Science Solution on Azure

• Prepare a model for deployment (20–25%)

• Deploy and retrain a model (10–15%)

Design and prepare a machine learning solution (20–25%)

Design a machine learning solution
• Determine the appropriate compute specifications for a training workload
• Describe model deployment requirements
• Select which development approach to use to build or train a model

Manage an Azure Machine Learning workspace

• Create an Azure Machine Learning workspace
• Manage a workspace by using developer tools for workspace interaction
• Set up Git integration for source control

Manage data in an Azure Machine Learning workspace

• Select Azure Storage resources
• Register and maintain datastores
• Create and manage data assets

Manage compute for experiments in Azure Machine Learning

• Create compute targets for experiments and training
• Select an environment for a machine learning use case
• Configure attached compute resources, including Apache Spark pools
• Monitor compute utilization

Explore data and train models (35–40%)

Explore data by using data assets and data stores
• Access and wrangle data during interactive development
• Wrangle interactive data with Apache Spark

Create models by using the Azure Machine Learning designer

• Create a training pipeline
• Consume data assets from the designer
• Use custom code components in designer
• Evaluate the model, including responsible AI guidelines

Use automated machine learning to explore optimal models

• Use automated machine learning for tabular data
• Use automated machine learning for computer vision
• Use automated machine learning for natural language processing (NLP)
• Select and understand training options, including preprocessing and algorithms

3
 Exam DP-100: Designing and Implementing a Data Science Solution on Azure

• Evaluate an automated machine learning run, including responsible AI guidelines

Use notebooks for custom model training

• Develop code by using a compute instance
• Track model training by using MLflow
• Evaluate a model
• Train a model by using Python SDK
• Use the terminal to configure a compute instance

Tune hyperparameters with Azure Machine Learning

• Select a sampling method
• Define the search space
• Define the primary metric
• Define early termination options

Prepare a model for deployment (20–25%)

Run model training scripts
• Configure job run settings for a script
• Configure compute for a job run
• Consume data from a data asset in a job
• Run a script as a job by using Azure Machine Learning
• Use MLflow to log metrics from a job run
• Use logs to troubleshoot job run errors
• Configure an environment for a job run
• Define parameters for a job

Implement training pipelines

• Create a pipeline
• Pass data between steps in a pipeline
• Run and schedule a pipeline
• Monitor pipeline runs
• Create custom components
• Use component-based pipelines

Manage models in Azure Machine Learning

• Describe MLflow model output
• Identify an appropriate framework to package a model
• Assess a model by using responsible AI guidelines

4
 Exam DP-100: Designing and Implementing a Data Science Solution on Azure

Deploy and retrain a model (10–15%)

Deploy a model
• Configure settings for online deployment
• Configure compute for a batch deployment
• Deploy a model to an online endpoint
• Deploy a model to a batch endpoint
• Test an online deployed service
• Invoke the batch endpoint to start a batch scoring job

Apply machine learning operations (MLOps) practices

• Trigger an Azure Machine Learning job, including from Azure DevOps or GitHub
• Automate model retraining based on new data additions or data changes
• Define event-based retraining triggers

Study resources
We recommend that you train and get hands-on experience before you take the exam. We offer self-
study options and classroom training as well as links to documentation, community sites, and videos.

Study resources Links to learning and documentation

Get trained Choose from self-paced learning paths and modules or take an
instructor led course

Find documentation Azure Databricks

Azure Machine Learning
Azure Synapse Analytics
MLflow and Azure Machine Learning

Ask a question Microsoft Q&A | Microsoft Docs

Get community support AI - Machine Learning - Microsoft Tech Community

AI - Machine Learning Blog - Microsoft Tech Community

Follow Microsoft Learn Microsoft Learn - Microsoft Tech Community

Find a video Microsoft Learn Shows

5
 Exam DP-100: Designing and Implementing a Data Science Solution on Azure

Change log
Key to understanding the table: The topic groups (also known as functional groups) are in bold typeface
followed by the objectives within each group. The table is a comparison between the two versions of
the exam skills measured and the third column describes the extent of the changes.

Skill area prior to March 14, 2023 Skill area as of March 14, 2023 Change

Design and prepare a machine Design and prepare a machine No % change

learning solution learning solution

Design a machine learning solution Design a machine learning solution No change

Manage an Azure Machine Learning Manage an Azure Machine Learning No change

workspace workspace

Manage data in an Azure Machine Manage data in an Azure Machine No change

Learning workspace Learning workspace

Manage compute for experiments in Manage compute for experiments in Minor

Azure Machine Learning Azure Machine Learning

Explore data, and train models Explore data and train models No % change

Explore data by using data assets and Explore data by using data assets and Major
data stores data stores

Create models by using the Azure Create models by using the Azure Minor
Machine Learning designer Machine Learning designer

Use automated machine learning to Use automated machine learning to No change

explore optimal models explore optimal models

Use notebooks for custom model Use notebooks for custom model Minor
training training

Tune hyperparameters with Azure Tune hyperparameters with Azure No change

Machine Learning Machine Learning

Prepare a model for deployment Prepare a model for deployment No % change

Run model training scripts Run model training scripts No change

Implement training pipelines Implement training pipelines No change

Manage models in Azure Machine Manage models in Azure Machine No change

Learning Learning

Deploy and retrain a model Deploy and retrain a model No % change

6
 Exam DP-100: Designing and Implementing a Data Science Solution on Azure

Skill area prior to March 14, 2023 Skill area as of March 14, 2023 Change

Deploy a model Deploy a model Minor

Apply machine learning operations Apply machine learning operations Minor

(MLOps) practices (MLOps) practices

Skills measured prior to March 14, 2023

Audience profile
Candidates for the Azure Data Scientist Associate certification should have subject matter expertise in
applying data science and machine learning to implement and run machine learning workloads on
Azure.
Responsibilities for this role include designing and creating a suitable working environment for data
science workloads; exploring data; training machine learning models; implementing pipelines; running
jobs to prepare for production; and managing, deploying, and monitoring scalable machine learning
solutions.
A candidate for this certification should have knowledge and experience in data science by using Azure
Machine Learning and MLflow.
• Design and prepare a machine learning solution (20–25%)
• Explore data, and train models (35–40%)
• Prepare a model for deployment (20–25%)
• Deploy and retrain a model (10–15%)

Design and prepare a machine learning solution (20–25%)

Design a machine learning solution
• Determine the appropriate compute specifications for a training workload
• Describe model deployment requirements
• Select which development approach to use to build or train a model

Manage an Azure Machine Learning workspace

• Create an Azure Machine Learning workspace
• Manage a workspace by using developer tools for workspace interaction
• Set up Git integration for source control

Manage data in an Azure Machine Learning workspace

• Select Azure Storage resources
• Register and maintain datastores
• Create and manage data assets

7
 Exam DP-100: Designing and Implementing a Data Science Solution on Azure

Manage compute for experiments in Azure Machine Learning

• Create compute targets for experiments and training
• Select an environment for a machine learning use case
• Configure attached compute resources, including Azure Databricks and Azure Synapse Analytics
• Monitor compute utilization

Explore data, and train models (35–40%)

Explore data by using data assets and data stores
• Load and transform data
• Analyze data by using Azure Data Explorer
• Use differential privacy

Create models by using the Azure Machine Learning designer

• Create a training pipeline
• Consume data assets from the designer
• Use designer components to define a pipeline data flow
• Use custom code components in designer
• Evaluate the model, including responsible AI guidelines

Use automated machine learning to explore optimal models

• Use automated machine learning for tabular data
• Use automated machine learning for computer vision
• Use automated machine learning for natural language processing (NLP)
• Select and understand training options, including preprocessing and algorithms
• Evaluate an automated machine learning run, including responsible AI guidelines

Use notebooks for custom model training

• Develop code by using a compute instance
• Consume data in a notebook
• Track model training by using MLflow
• Evaluate a model
• Train a model by using Python SDKv2
• Use the terminal to configure a compute instance

Tune hyperparameters with Azure Machine Learning

• Select a sampling method
• Define the search space
• Define the primary metric
• Define early termination options

8
 Exam DP-100: Designing and Implementing a Data Science Solution on Azure

Prepare a model for deployment (20–25%)

Run model training scripts
• Configure job run settings for a script
• Configure compute for a job run
• Consume data from a data asset in a job
• Run a script as a job by using Azure Machine Learning
• Use MLflow to log metrics from a job run
• Use logs to troubleshoot job run errors
• Configure an environment for a job run
• Define parameters for a job

Implement training pipelines

• Create a pipeline
• Pass data between steps in a pipeline
• Run and schedule a pipeline
• Monitor pipeline runs
• Create custom components
• Use component-based pipelines

Manage models in Azure Machine Learning

• Describe MLflow model output
• Identify an appropriate framework to package a model
• Assess a model by using responsible AI guidelines

Deploy and retrain a model (10–15%)

Deploy a model
• Configure settings for real-time deployment
• Configure compute for a batch deployment
• Deploy a model to a real-time endpoint
• Deploy a model to a batch endpoint
• Test a real-time deployed service
• Invoke the batch endpoint to start a batch scoring job

Apply machine learning operations (MLOps) practices

• Trigger an Azure Machine Learning pipeline, including from Azure DevOps or GitHub
• Automate model retraining based on new data additions or data changes
• Define event-based retraining triggers