about this book

Machine Learning System Design is a comprehensive step-by-step guide designed to help you work on your ML system at every stage of its creation—from gathering information and taking preliminary steps to implementation, release, and ongoing maintenance.

As the title suggests, the book is dedicated to ML system design, not focusing on a particular technology but rather providing a high-level framework on how to approach problems related to building, maintaining, and improving ML systems of various scales and levels of complexity.

As ML and AI are getting bigger and bigger these days, there are many books and courses on algorithms, domains, and other specific aspects. However, they don’t provide an entire vision. This leads to the problem Arseny and Valerii have seen in multiple companies, where solid engineers successfully build scattered subcomponents that can’t be combined into a fully functioning, reliable system. This book aims to, among other things, fill this gap.

This book is not beginner friendly. We expect our readers to be familiar with ML basics (you can understand an ML textbook for undergraduate students) and to be fluent in applied programming (you have faced real programming challenges outside the studying sandbox).

Who should read this book?

We hope this book will be helpful to

Mid-career engineers: to hone their skills in building and maintaining solid ML systems and make sure they don’t miss anything critical.
Engineering managers and senior engineers: to fill the gaps in their knowledge and view ML system design from a broader perspective.
Those starting their journey in applied ML: to have structured guidelines at hand before kicking off their first ML system.

How this book is organized: A roadmap

The book structure is designed as a checklist or manual, with an infusion of campfire stories from our own experience. It can be read all at once or used at any moment while working on a specific aspect of a ML system. At the same time, we try not to slip into sounding like a typical textbook or course on classic machine learning or deep learning.

We’ve split the book into four main parts so that its structure is in line with the life cycle of any system:

Discovery
Building a core
Improvement
Maintenance

Chapters 1–8 are based around the early stages of ML system design. Throughout chapters 1–4, we focus on overall awareness and understanding of the problem your system needs to solve and define the steps needed before system development has started. This phase rarely involves writing code and mostly focuses on small prototypes or proofs of concepts.

Chapters 5–8 delve into the technical details of the early-stage work. This stage requires a lot of reading and communicating, which is crucial for understanding a problem, defining a landscape for possible solutions, and aligning expectations with other project participants. If we compare an ML system to a human body, it’s about forming a skeleton.

Chapters 9–12 are focused on intermediate steps. At this stage of the system life cycle, the schedule of responsible engineers is usually flipped, and there is way less research and communication and more hands-on work on implementing and improving the system. Here, we focus on such questions as how to make the system solid, accurate, and reliable. Continuing the human body metaphor, this is where the system grows its muscles.

The final part, featuring chapters 13–16, is dedicated to integration and growth. For an inexperienced observer, the system may seem ready to go, but this is a tricky impression. There are multiple (mostly engineering-related) aspects that need to be taken into account before the system goes live successfully. In the software world, a system failure is rarely a disaster like in civil engineering, but it’s still an unwanted scenario. So at this stage you will learn how to make your system reliable, maintainable, and future-proof. If you’re still not tired of human body metaphors, this is where the system gets its wisdom, because untamed strength can lead to nothing but trouble.

liveBook discussion forum

Purchase of Machine Learning System Design includes free access to liveBook, Manning’s online reading platform. Using liveBook’s exclusive discussion features, you can attach comments to the book globally or to specific sections or paragraphs. It’s a snap to make notes for yourself, ask and answer technical questions, and receive help from the author and other users. To access the forum, go to . You can also learn more about Manning’s forums and the rules of conduct at .

Manning’s commitment to our readers is to provide a venue where a meaningful dialogue between individual readers and between readers and the authors can take place. It is not a commitment to any specific amount of participation on the part of the authors, whose contribution to the forum remains voluntary (and unpaid). We suggest you try asking them some challenging questions lest their interest stray! The forum and the archives of previous discussions will be accessible from the publisher’s website for as long as the book is in print.