This book provides a comprehensive review of computational analytics methods and techniques. It is a rich and readable summary of the field. The approach here is to augment statistical approaches with techniques from symbolic artificial intelligence (AI) and machine learning. The book serves both as a university textbook and as a reference book for researchers and practitioners in business analytics. It will be beneficial to those who seek to build analytics systems grounded in theory that is well founded rather than ad hoc.

This book consists of 16 chapters organized under six headings. The first is an introduction to the concepts of analytics and basic probability and statistics. The second covers a range of basic topics in statistical analytics. Taken together, these first two sections cover the typical subject matter of a course in mathematical statistics. The third section includes five chapters that deal with AI for analytics. Topics covered include symbolic AI, uncertainty, belief network models, prescriptive models, influence diagrams, temporal models, nonlinear models, and particle filters. The fourth section examines machine learning in analytics. Topics here include clustering techniques for segmenting data, including feed-forward neural networks. Also included are algorithms for learning decision trees and inductive logic programming. The fifth section in this book focuses on information structuring and dissemination. It begins with a discussion of the analytics of unstructured textual data, including information extraction, text classifications, and popular linguistic techniques for analysis. It continues with a discussion of the standardization of information content for comprehension by various consumers of the information, and it concludes with the semantic web technology as an example. The last section builds upon previous chapters and presents several analytics tools and case studies. In addition to exploring important analytics tools that are commercially available in the analytics marketplace, the author of this book has also developed three tools for analytics. He discusses one for implementing machine learning techniques, one for extracting and classifying text documents, and one that provides a development environment with an embedded expert system shell. The book concludes with four case studies. These cases address risk assessment analytics in lending, financial fraud detection analytics, sentiment analytics in textual data, and life status analytics and mortality.

Analytics is a broadly interdisciplinary topic. This book reflects an ambitiously comprehensive computational account of analytics. It brings a range of current topics together under one cover and provides a valuable reference resource for serious-minded analytics professionals.