DP-100 Data Science on Azure

Skill Goal:

Develop foundational knowledge of data science concepts and how Microsoft Azure supports data science solutions.

Skills Developed:

• Explain core data science concepts and methodologies

• Describe the data science lifecycle and common workflows

• Identify Azure services used in data science projects

• Navigate the Azure Portal and explore data science–related resources

• Set up and manage an Azure account for data science workloads

Sprint Outcome:

Ability to understand the data science lifecycle and identify appropriate Azure services to support data science solutions.

Skill Goal:

Apply data exploration and preparation techniques using Azure tools.

Skills Developed:

• Work with structured and unstructured data sources

• Perform exploratory data analysis (EDA)

• Clean and transform datasets (handle missing values, outliers, duplicates)

• Understand data ingestion workflows in Azure

• Use Azure Data Factory and Azure Databricks for data preparation

Sprint Outcome:

Ability to explore, clean, and prepare datasets using Azure-based data processing tools.

Skill Goal:

Build practical understanding of machine learning concepts and model selection strategies.

Skills Developed:

• Differentiate supervised, unsupervised, and reinforcement learning

• Classify problems as regression, classification, or clustering

• Understand the machine learning lifecycle

• Identify common machine learning algorithms and use cases

• Prepare datasets conceptually for ML model training

Sprint Outcome:

Ability to identify appropriate machine learning approaches for different business problems.

Skill Goal:

Develop, train, and evaluate machine learning models using Azure Machine Learning.

Skills Developed:

• Create and manage Azure Machine Learning workspaces

• Use Azure ML Studio for model development

• Split datasets into training, validation, and test sets

• Train models using Azure ML tools

• Evaluate models using standard performance metrics

• Apply basic hyperparameter tuning techniques

Sprint Outcome:

Ability to build, train, and evaluate machine learning models using Azure Machine Learning.

Skill Goal:

Deploy, manage, and monitor machine learning models in production environments.

Skills Developed:

• Understand model deployment concepts in Azure

• Deploy models as REST endpoints/web services

• Use Azure Kubernetes Service (AKS) for scalable deployments

• Manage model versions and lifecycle

• Monitor model performance and reliability

Sprint Outcome:

Ability to deploy and manage scalable, production-ready machine learning solutions in Azure.

Skill Goal:

Apply Azure Cognitive Services to solve real-world AI problems.

Skills Developed:

• Identify Azure Cognitive Services offerings and capabilities

• Implement Computer Vision solutions

• Apply Text Analytics for sentiment analysis and language detection

• Use Speech services for speech-to-text and text-to-speech

• Integrate Cognitive Services into applications

Sprint Outcome:

Ability to implement and integrate Azure Cognitive Services into business solutions.

Skill Goal:

Design secure, scalable, and production-ready data science solutions using Azure services.

Skills Developed:

• Design end-to-end Azure ML architectures

• Select appropriate Azure services for different ML workloads

• Integrate data pipelines, modeling workflows, and deployment components

• Apply security, compliance, and governance best practices

• Evaluate cost, scalability, and performance considerations

Sprint Outcome:

Ability to design complete Azure-based data science solutions aligned with business and technical requirements.

Skill Goal:

Prepare effectively for the DP-100 certification exam.

Skills Developed:

• Understand DP-100 exam domains and objectives

• Map Skills Sprints to certification competencies

• Identify common exam question patterns

• Apply exam preparation strategies

• Assess readiness through practice-style scenarios

Sprint Outcome:

Ability to confidently approach and prepare for the DP-100 certification exam.

Project Goal:

Design, build, deploy, and present an end-to-end Azure-based data science solution that solves a real-world business problem using machine learning and Azure AI services.

Skills Demonstrated:

• Analyze a real-world business problem requiring predictive or analytical modeling

• Identify appropriate Azure data services for ingestion, storage, and processing

• Design a complete Azure Machine Learning solution architecture

• Prepare, clean, and transform datasets for modeling

• Build, train, and evaluate machine learning models using Azure Machine Learning

• Apply appropriate evaluation metrics based on the problem type (classification, regression, clustering)

• Deploy a trained model as a scalable Azure endpoint

• Implement monitoring and model lifecycle management practices

• Integrate Azure Cognitive Services where applicable

• Apply responsible AI principles and governance best practices

• Evaluate scalability, cost, and performance considerations

• Present a production-ready, secure, and business-aligned data science solution