Principles of Data Mining

This book explains and explores the main techniques of data mining, the automatic extraction of useful implicit and potentially useful information from data, which are increasingly used in commercial, scientific, and other applications. It focuses on classification and mining of link and agglomeration bases. Each topic is clearly explained, with an emphasis on algorithms rather than mathematical formalism, and is illustrated through detailed practical examples. The book is written for readers who do not have a strong background in mathematics or statistics and any formulas used are explained in detail. It can be used as a textbook to support undergraduate or graduate courses in a wide range of subjects including computer science, business studies, marketing, artificial intelligence, bioinformatics, and forensic science. As a self-study aid, this book is intended to help readers in general develop the necessary understanding of what is inside the "black box" so that they can discriminately use commercial data mining packages, as well as to enable advanced readers or academic researchers to understand or contribute to technical advances future in this field. Each chapter contains 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 data flows, both static data, where the base model is fixed, and time-dependent data, where the base model changes from time to time - a phenomenon known as concept skew.