October 2017 update (version 0.1.1710.04013) is now available. See release notes.
Getting Started

Get Started

What is Azure ML?

What is Azure ML?

Azure Machine Learning is an integrated, end-to-end data science and advanced analytics solution. It enables data scientists to prepare data, develop experiments and deploy models at cloud scale.
Getting Started on Data Prep

Data Preparation

Data Preparation provides a set of tools for efficiently exploring, understanding, and fixing problems in data. It allows you to consume data in many forms and transform that data into cleansed data that is better suited for downstream usage.
Configure Execution


Experimentation service allows data scientists to execute their experiments locally, in Docker containers, or in Spark clusters through simple configuration. It manages run history, provides version control, and enables sharing and collaboration.
Model Management

Model Management

Model management enables data scientists to manage and deploy machine-learning workflows and models as containerized web services. It provides flexibility for on-prem, IoT edge, as well as cloud-based deployment. It also enables model versioning, telemetry tracking and more.
Workbench Quick Tour





(Create a new project using one of these examples)
QnA Matching
An easy development process for building question and answer matching solution
Document Collection Analysis
Summarize and analyze a large collection of documents using data from the US Congress
Biomedical Entity Recognition - TDSP Example
Entity Extraction illustrated using a text corpus from healthcare
Aerial Image Classification
Distributed training and operationalization of image classification models
Server Workload Forecasting on Terabytes Data
Use Azure ML Workbench to develop end-to-end solutions that require use of big data
Predictive Maintenance
End-to-end solution written in PySpark for predictive maintenance use case
Energy Demand Time Series Forecasting
End-to-end solution for predicting the future load on energy grid
Customer Churn Prediction
End-to-end solution for prediction of customer churn
Sentiment Analysis with Deep Learning
Sentiment analysis using CNTK as the backend for Keras
Distributed Tuning of Hyperparameters
Scale out tuning of hyperparameters using Docker container and Spark cluster
Classify US Incomes - TDSP Example
Predict annual income of individuals, following Team Data Science Process
Team Data Science Process Template
An agile, iterative, data science methodology to improve team collaboration and learning.