Mastering machine learning with R

Machine learning is the branch of artificial intelligence concerned with systems that improve by studying data. This guide shows how to apply those methods with R, a free statistical programming language that runs on every major operating system. It is aimed at readers who want to tackle demanding business problems with R and who already have some experience with the language and a basic grounding in statistics or machine learning.

The book begins with the Cross-Industry Standard Process for Data Mining, a framework for organising analytical projects. From there it covers multivariate regression in depth, followed by classification and regression trees. Two unsupervised techniques are then introduced, and the final chapters address text analysis and time series.

Along the way, readers learn to reshape data in R so it is ready for analysis, to choose suitable visualisations, and to split data into training and test sets. The methods covered include linear and logistic regression and, for more advanced work, support vector machines. Practical examples include building complex recommendation systems.

The writing pairs clear explanations of difficult theory with applied, real-world examples, and it is candid about where each method falls short. By the end, readers should be able to design and carry out complete machine learning projects in R using its packages.