Principles of Data Mining

Description

This book explains and explores the principal techniques of Data Mining, the automatic extraction of implicit and potentially useful information from data, which is increasingly used in commercial, scientific and other application areas. It focuses on classification, association rule mining and clustering. Each topic is clearly explained, with a focus on algorithms not mathematical formalism, and is illustrated by detailed worked examples. The book is written for readers without a strong background in mathematics or statistics and any formulae used are explained in detail. It can be used as a textbook to support courses at undergraduate or postgraduate levels in a wide range of subjects including Computer Science, Business Studies, Marketing, Artificial Intelligence, Bioinformatics and Forensic Science. As an aid to self study, this book aims to help general readers develop the necessary understanding of what is inside the 'black box' so they can use commercial data mining packages discriminatingly, as well as enabling advanced readers or academic researchers to understand or contribute to future technical advances in the field. Each chapter has practical exercises to enable readers to check their progress. A full glossary of technical terms used is included. This expanded third edition includes detailed descriptions of algorithms for classifying streaming data, both stationary data, where the underlying model is fixed, and data that is time-dependent, where the underlying model changes from time to time - a phenomenon known as concept drift Front Matter....Pages I-XV Introduction to Data Mining....Pages 1-8 Data for Data Mining....Pages 9-19 Introduction to Classification: Naïve Bayes and Nearest Neighbour....Pages 21-37 Using Decision Trees for Classification....Pages 39-48 Decision Tree Induction: Using Entropy for Attribute Selection....Pages 49-62 Decision Tree Induction: Using Frequency Tables for Attribute Selection....Pages 63-78 Estimating the Predictive Accuracy of a Classifier....Pages 79-92 Continuous Attributes....Pages 93-119 Avoiding Overfitting of Decision Trees....Pages 121-136 More About Entropy....Pages 137-156 Inducing Modular Rules for Classification....Pages 157-174 Measuring the Performance of a Classifier....Pages 175-187 Dealing with Large Volumes of Data....Pages 189-208 Ensemble Classification....Pages 209-220 Comparing Classifiers....Pages 221-236 Association Rule Mining I....Pages 237-251 Association Rule Mining II....Pages 253-269 Association Rule Mining III: Frequent Pattern Trees....Pages 271-309 Clustering....Pages 311-328 Text Mining....Pages 329-343 Classifying Streaming Data....Pages 345-378 Classifying Streaming Data II: Time-Dependent Data....Pages 379-425 Back Matter....Pages 427-526