Time series forecasting with Azure Machine Learning

Description

Time series modeling and forecasting is fundamentally important to various practical domains; in the past few decades, machine learning model-based forecasting has become very popular in both private and public decision-making processes.

Azure Machine Learning is a cloud service that you can use to track your models as you build, train, deploy, and manage them, all at the broad scale that the cloud provides. Francesca Lazzeri walks you through using Azure Machine Learning to build and deploy your time series forecasting models.

Outline

Introduction to Azure Machine Learning

• Set up your development environment
• Access and examine external data
• Train a simple model locally using the popular scikit-learn machine learning library
• Train multiple models on a remote cluster
• Review training results and register the best model
• Deploy your model as web service

Introduction to time series forecasting

• What makes time series special?
• Loading and handling time series in pandas
• How to check stationarity of a time series?
• How to make a time series stationary?
• Classical methods for forecasting a time series
• Neural networks for time series forecasting

Energy demand forecasting: A use case

• Introduction to the use case
• Dataset exploration
• Feature engineering
• Data preprocessing

Automated machine learning in Azure Machine Learning

• How to generate a forecast machine learning model using automated machine learning
• Perform data preprocessing with automated machine learning
• Perform algorithm selection with automated machine learning
• Perform hyperparameter selection with automated machine learning