Develop smart applications without spending days and weeks building machine-learning models. With this practical book, you’ll learn how to apply Automated Machine Learning, a process that uses machine learning to help people build machine learning models. Deepak Mukunthu, Parashar Shah, and Wee Hyong Tok provide a mix of technical depth, hands-on examples, and case studies that show how customers are solving real-world problems with this technology.

Building machine learning models is an iterative and time-consuming process. Even those who know how to create these models may be limited in how much they can explore. Once you complete this book, you’ll understand how to apply Automated Machine Learning to your data right away.

• Learn how companies in different industries are benefiting from Automated Machine Learning
• Get started with Automated Machine Learning using Azure
• Explore aspects such as algorithm selection, auto featurization, and hyperparameter tuning
• Understand how data analysts, BI professionals, and developers can use Automated Machine Learning in their familiar tools and experiences
• Learn how to get started using Automated Machine Learning for use cases including classification and regression.

Table of Contents

Part I. Automated Machine l earning

Chapter 1. Machine l earning: Overview and Best Practices

Chapter 2. How Automated Machine Learning Works

Part II. Automated Ml on Azure

Chapter 3. Getting Started with Microsoft Azure Machine Learning and Automated ML

Chapter 4. Feature Engineering and Automated Machine Learning

Chapter 5. Deploying Automated Machine Learning Models

Chapter 6. Classification and Regression

Part Ill. How Enterprises Are Using Automated Machine l earning

Chapter 7. Model lnterpretability and Transparency with Automated ML

Chapter 8. Automated ML for Developers

Chapter 9. Automated ML for Everyone

I vividly remember my first undergraduate class in artificial intelligence (AI). My father had worked for years on “expert systems,” and I was at MIT to learn from the best how to perform this wizardry. Marvin Minsky, one of the founders of the field, even taught a series of guest lectures there. It was about midway through the semester when the great disillusionment hit me: “It’s all just a bunch of tricks!” There was no “intelligence” to be found; just a bunch of brittle rules engines and clever use of math. This was in the early ’90s and the start of my own personal AI winter, when I dismissed AI as not having much use.

Years later, while I was working on advertising systems, I finally saw that there was power in this “bunch of tricks.” Algorithms that had been hand-tuned for months by talented engineers were being beaten by simple models provided with lots of data. I saw that the explosion that was to come simply needed more data and more computation to be effective.

Over the past 5 to 10 years, the explosion in both big data and computation power has unleashed an industry that has had lots of starts and stops to it.

This time is different. While the hype about AI is still tremendously high, the potential applications of practical AI have really just begun to hit the business world.

The rules/people making predictions today will be replaced virtually every place by AI algorithms. The value AI creates for businesses is tremendous, from being better able to value the oil available in an oil field to better predicting the inventory a store should stock of each new sneaker. Even marginal improvements in these capabilities represent billions of dollars of value across businesses.

We’re now in an age of AI implementation. Companies are working to find all the best places to deploy AI in their enterprises. One of the biggest challenges is matching the hype to reality. Half the companies I’ve talked to expect AI to perform some kind of magic for problems they have no idea how to solve. The other half are underestimating the power that AI can have. What they need are people with enough background in AI to help them conceive of what is possible and apply it to their business problems.

Customers I talk to are struggling to find enough people with those skills. While they have lots of developers and data analysts who are skilled and comfortable making predictions and decisions with data, they need data scientists who can then build the model from that data. This book will help fill that gap.

It shows how automated ML can empower developers and data analysts to train AI models. It highlights a number of business cases where AI is a great fit to the business problem and show exactly how to build that model and put it into production.

The technology and ideas in this book have been pressure-tested at scale with teams all across Microsoft, including Bing, Office, Azure Security, internal IT, and many more. It’s also been used by many external businesses using Azure Machine Learning.

Eric Boyd

Microsoft Corporate Vice President, Azure AI

September 2019

About the Author

Deepak Mukunthu is a product leader with more than 16 years of experience. With his experience in big data, analytics, and AI, Deepak has played instrumental leadership roles in helping organizations and teams become data-driven and to adopt machine learning. He brings a good mix of thought leadership, customer understanding, and innovation to design and deliver compelling products that resonate well with customers. In his current role of principal program manager of the automated ML in Azure AI platform group at Microsoft, Deepak drives product strategy and roadmap for Automated ML with the goal of accelerating AI for data scientists and democratizing AI for other personas interested in machine learning. In addition to shaping the product direction, he also plays an instrumental role in helping customers adopt Automated ML for their business-critical scenarios. Prior to joining Microsoft, Deepak worked at Trilogy where he played multiple roles―consultant, business development, program manager, engineering manager―successfully leading distributed teams across the globe and managing technical integration of acquisitions.

Parashar Shah is a senior program/product manager on the Azure AI engineering team at Microsoft, leading big data and deep learning projects to help increase adoption of AI in enterprises especially automated ML with Spark. At Microsoft and at Alcatel-Lucent/Bell Labs prior to that, his contributions increased global adoption of AI/analytics platform contributing to customers' growth in retail, manufacturing, telco, and oil and gas verticals. Parashar has an MBA from the Indian Institute of Management Bangalore and a B.E. (E.C.) from Nirma Institute of Technology, Ahmedabad. He also cofounded a carpool startup in India. He has also coauthored Hands-On Machine Learning with Azure: Build Powerful Models with Cognitive Machine Learning and Artificial Intelligence (Packt), published in November 2018. He has filed for five patents. He has presented at multiple Microsoft and external conferences, including Spark summit and KDD. His interests span the subjects of photography, AI, machine learning, automated ML, big data, and the internet of things (IoT).

Wee Hyong Tok is part of the AzureCAT team at Microsoft. He has extensive leadership experience leading multidisciplinary team of engineers and data scientists, working on cutting-edge AI capabilities that are infused into products and services. He is a tech visionary with a background in product management, machine learning/deep learning and working on complex engagements with customers. Over the years, he has demonstrated that his early thought leadership whitepapers on tech trends have become reality, and deeply integrated into many products. His ability to strategize, and turn strategy to execution, and hunting for customer adoption has enabled many projects that he works on to be successful. He is continuously pushing the boundaries of products for machine learning and deep learning. His team works extensively with deep learning frameworks, ranging from TensorFlow, CNTK, Keras, and PyTorch. Wee Hyong has worn many hats in his career―developer, program/product manager, data scientist, researcher, and strategist―and his range of experience has given him unique superpowers to lead and define the strategy for high-performing data and AI innovation teams. Throughout his career, he has been a trusted advisor to the C-suite, from Fortune 500 companies to startups.