Ye N. Data Mining: Theories, Algorithms, and Examples

N.-Y.: CRC Perss, 2013. — 347 p. — e-ISBN: 978-1-4822-1936-4.Technologies have enabled us to collect massive amounts of data in many fields. However, our pace of discovering useful information and knowledge from these data falls far behind our pace of collecting the data. Conversion of massive data into useful information and knowledge involves two steps: (1) mining patterns present in the data and (2) interpreting those data patterns in their problem domains to turn them into useful information and knowledge. There exist many data mining algorithms to automate the first step of mining various types of data patterns from massive data.
Interpretation of data patterns usually depend on specific domain knowledge and analytical thinking. This book covers data mining algorithms that can be used to mine various types of data patterns. Learning and applying data mining algorithms will enable us to automate and thus speed up the first step of uncovering data patterns from massive data. Understanding how data patterns are uncovered by data mining algorithms is also crucial to carrying out the second step of looking into the meaning of data patterns in problem domains and turning data patterns into useful information and knowledge.The data mining algorithms in this book are organized into five parts for mining five types of data patterns from massive data, as follows:
Classification and prediction patterns;
Cluster and association patterns;
Data reduction patterns;
Outlier and anomaly patterns;
Sequential and temporal patterns.As stated earlier, mining data patterns from massive data is only the first step of turning massive data into useful information and knowledge in problem domains. Data patterns need to be understood and interpreted in their problem domain in order to be useful. To apply a data mining algorithm and acquire the ability of understanding and interpreting data patterns produced
by that data mining algorithm, we need to understand two important aspects of the algorithm:
Theoretical concepts that establish the rationale of why elements of the data mining algorithm are put together in a specific way to mine a particular type of data pattern
Operational steps and details of how the data mining algorithm processes massive data to produce data patterns.
This book aims at providing both theoretical concepts and operational details of data mining algorithms in each chapter in a self-contained, complete manner with small data examples. It will enable readers to understand theoretical and operational aspects of data mining algorithms and to manually execute the algorithms for a thorough understanding of the data patterns
produced by them.