Hands-On Automated Machine Learning: A beginner’s guide to building automated machine learning systems using AutoML and Python

Automating a machine-learning workflow is more than choosing a model with a button. It means deciding what can be automated, preparing data carefully, comparing approaches, and understanding the trade-offs behind the results. Hands-On Automated Machine Learning takes readers through those connected decisions with Python examples and a practical focus on building AutoML components.

Start with the foundations, then automate

Sibanjan Das and Umit Mert Cakmak begin with core machine-learning ideas before turning to the stages that make up an automated workflow. The early chapters cover supervised and unsupervised learning, common algorithms, evaluation, and data preparation—useful groundwork for understanding what an AutoML system is doing behind the scenes.

See the moving parts of an AutoML workflow

The book examines feature preprocessing, feature selection and generation, algorithm selection, and hyperparameter optimization as distinct challenges. It introduces open-source tools such as auto-sklearn and MLBox, and considers how individual components can be assembled into pipelines or developed into custom automation modules.

• Prepare numerical, categorical, and text data, and consider missing values and outliers.
• Compare algorithms and explore supervised and unsupervised learning approaches.
• Study hyperparameter tuning, including Bayesian-based methods.
• Build machine-learning pipelines and examine neural networks, autoencoders, and convolutional neural networks.

Keep the project context in view

Automation does not remove the need to make informed choices. The book also discusses computational complexity, model trade-offs, and the phases of a data-science engagement—from business and data understanding through evaluation and deployment. That perspective helps place technical choices within the larger work of solving a problem with data.

Who may find it useful?

This introductory guide is relevant to data scientists, data analysts, machine-learning enthusiasts, and practitioners interested in Python-based AutoML workflows. Some familiarity with Python is helpful; readers will encounter both foundational machine-learning concepts and practical automation topics.

For readers who want to understand how the pieces of an automated machine-learning pipeline fit together, this book offers a structured place to begin.