Feature Engineering for Machine Learning: Principles and Techniques for Data

Zheng and Casari’s Feature Engineering for Machine Learning fills a vital gap in the data science literature by treating feature creation as a systematic discipline rather than an art form. The text focuses on building intuition: why certain transformations work, when to apply them, and how they affect learning algorithms. Readers explore feature construction strategies for numerical, categorical, text, and time-based data, illustrated through detailed case studies. The book’s strength lies in its applied orientation - each chapter connects data preprocessing with measurable model improvement, making it invaluable for practitioners who want to move beyond automated pipelines and truly understand the data they shape. The prose is concise yet rich with insight, making it accessible to both analysts and engineers. While it assumes some prior knowledge of Python and machine learning, it rewards the reader with a practical framework for thinking about data creatively and analytically. This focus on craftsmanship over automation makes it a lasting reference in any data scientist’s library.

Alice Zheng is a machine learning researcher and data scientist with experience at Amazon and Microsoft, focusing on large-scale model development and education. Amanda Casari is a research scientist at Google, specializing in applied machine learning and data engineering practices.