Data Mining And Business Analytics With R

Careful analysis of data is becoming more and more critical in business. Across large businesses such as Google, Netflix, and Amazon, large amounts of data are gathered on matters such as customer behavior and purchase history. To correctly understand and gather valuable information from this data, it is essential that researchers are equipped with the appropriate, easily-accessible computational and analytical tools. Business Analytics and Data Mining with R showcases the powerful computing capabilities of R software for extracting and analyzing information taken from large sets of data to identify meaningful patterns. While most literature on the topic utilizes expensive and complex software, this book utilizes the freely-available R software for the analysis, exploration, and simplification of large high-dimensional datasets. As a result, readers are provided with the needed guidance to model and interpret complicated data and become adept at building powerful models for prediction and classification. Highlighting both basic underlying concepts and practical computational skills, the book begins with coverage of standard linear regression and importance of parsimony in statistical modeling. Subsequent chapters feature topical coverage of: penalty-based variable selection in regression models with many parameters (LASSO); logistic regression; binary classification, probabilities and evaluating classification performance; classification using a nearest neighbor analysis; the Naive Bayesian analysis; multinomial logistic regression; more on classification, and a discussion of discriminant analysis; decision trees; clustering; market basket analysis; dimension reduction; principal components regression and partial least squares; text mining and sentiment analysis; and analysis of network data. An extensive related Web site features R sample programs and R code as well as additional data sets and exercises, providing readers with opportunities to work with the discussed material hands-on.

JOHANNES LEDOLTER, PhD, is Professor in both the Department of Management Sciences and the Department of Statistics and Actuarial Science at the University of Iowa. He is a Fellow of the American Statistical Association and the American Society for Quality, and an Elected Member of the International Statistical Institute. Dr. Ledolter is the coauthor of Statistical Methods for Forecasting, Achieving Quality Through Continual Improvement, and Statistical Quality Control: Strategies and Tools for Continual Improvement, all published by Wiley.