Presented By
O’Reilly + Cloudera
Make Data Work
29 April–2 May 2019
London, UK

Time series forecasting with Azure Machine Learning

Francesca Lazzeri (Microsoft), Aashish Bhateja (Microsoft)
13:3017:00 Tuesday, 30 April 2019
Data Science, Machine Learning & AI
Location: Capital Suite 2/3
Average rating: ****.
(4.25, 4 ratings)

Who is this presentation for?

  • Data scientists, machine learning engineers, and AI developers

Level

Intermediate

Prerequisite knowledge

  • A working knowledge of Python
  • A basic understanding of machine learning and deep learning topics and terminology
  • Familiarity with time series forecasting (useful but not required)

Materials or downloads needed in advance

  • A laptop with an up-to-date version of Edge or Chrome installed
  • An Azure subscription (A free account is fine.)

What you'll learn

  • Understand the key concepts and principles of time series forecasting
  • Learn how to set up a Azure Machine Learning development environment, access and examine external data, build different machine learning models, review training results, register the best model, deploy it, and test it

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
Photo of Francesca Lazzeri

Francesca Lazzeri

Microsoft

Francesca Lazzeri is a senior machine learning scientist at Microsoft on the cloud advocacy team and an expert in big data technology innovations and the applications of machine learning-based solutions to real-world problems. Her research has spanned the areas of machine learning, statistical modeling, time series econometrics and forecasting, and a range of industries—energy, oil and gas, retail, aerospace, healthcare, and professional services. Previously, she was a research fellow in business economics at Harvard Business School, where she performed statistical and econometric analysis within the technology and operations management unit. At Harvard, she worked on multiple patent, publication and social network data-driven projects to investigate and measure the impact of external knowledge networks on companies’ competitiveness and innovation. Francesca periodically teaches applied analytics and machine learning classes at universities and research institutions around the world. She’s a data science mentor for PhD and postdoc students at the Massachusetts Institute of Technology and speaker at academic and industry conferences—where she shares her knowledge and passion for AI, machine learning, and coding.

Photo of Aashish Bhateja

Aashish Bhateja

Microsoft

Aashish Bhateja is a senior program manager working on Microsoft Azure Machine Learning—building an exciting machine learning service that makes it easy for all data scientists and ML engineers to create and deploy robust, scalable, and highly available machine learning web services in the cloud.