Clustering for Data Mining: A Data Recovery Approach

Description

This book gives a smooth, motivated and example-richintroduction to clustering, which is innovative in many aspects.Answers to important questions that are very rarely addressed if addressed at all, are provided.Examples:(a) what to do if the user has no idea of the numberof clusters and/or their location - use what is called intelligent k-means;(b) what to do if the data contain both numeric and categoricalfeatures - use what is called three-step standardization procedure;(c) how to catch anomalous patterns, (d) how to validate clusters, etc.Some of these may be subject to criticism, however some motivation is alwayssupplied, and the results are always reproducible thus testable.The book introduces a numberof non-conventional cluster interpretation aids derived from a datageometry view accepted by the author and based on what is referredthe contribution weights - basically showing those elements of clusterstructures that distinguish clusters from the rest. These contributionweights, applied to categorical data, appear to be highly compatiblewith what statisticians such as A. Quetelet and K. Pearson were developingin the past couple of centuries, which is a highly original and welcomedevelopment. The book reviews a rich set of approaches being accumulatedin such hot areas as text mining and bioinformatics, and shows thatclustering is not just a set of naive methods for data processing butforms an evolving area of data science.I adopted the book as a text for my courses in data mining for bachelorand master degrees.