Learning about data science

This page reviews textbooks on data science and machine learning. Reviewers’ credibility depends on their background reading. The reviews below cover various areas in data science.

Data Science here refers broadly to statistical analysis using computers. Wikipedia provides a comprehensive introduction.

An Introduction to Statistical Learning

This textbook presents and applies statistical techniques to investigate case studies. Each chapter includes practice problems to solve, often using R.

This textbook introduces the subject effectively. Readers seeking a quick review of available techniques will find it useful.

Elements of Statistical learning

Elements of Statistical Learning provides rigorous coverage of statistical methods. The book explores the theory behind ISL’s techniques in depth. The questions are substantive and demanding. A detailed solutions manual is available here.

This book suits readers seeking deep theoretical understanding. Working through the questions prepares well for specialised data science roles.

Linear Algebra and Learning from Data

This book covers linear algebra, statistics, optimisation and their data science applications. It suits undergraduates well; each chapter builds understanding through targeted problems. A full review appears in another post.

The book excels at covering fundamentals, though it may not warrant a second read.

Doing Data Science

This book provides practical insight into the data science process and key concepts. Chapters cover how data science applies to recommendation engines, fraud detection, and epidemiology. The section on Claudia Perlich’s experience competing in data science competitions and working in industry shows how successful practitioners operate.

This book complements theoretical texts by illustrating how to apply mathematical techniques. It emphasises decision-making in problem-solving rather than presenting equations in isolation.