Kohonen, T. (2001). 3rd edition. Springer-Verlag Berlin Heidelberg
This standard lecture book is the basic monograph on self-organizing maps (SOMs), written by the originator of the subject, Teuvo Kohonen.
SOM, with its variants, is the most popular artificial neural network algorithm in the unsupervised learning category. Many fields of science, including customer analytics, financial analyses, signal processing, engineering, medicine and life sciences, have adopted the SOM as a standard analytical tool.
Viscovery SOMine is reviewed in the book as a commercial standard tool for creating SOM applications.
Oja, E., & Kaski, S. (Eds.) (1999). Elsevier Science B.V.
Top experts in the SOM method cover the state of the art and the future of the theory. The thirty chapters of this book cover the current status of SOM theory, such as the role of SOMs in clustering, classification, probabilistic models, and energy functions. Many SOM applications are described, with an emphasis on data mining and exploratory data analysis as applied to large databases of financial data, medical data, free-form text documents, digital images, speech, and process measurements. Biological models related to the SOM are discussed as well.
In the chapter "Value maps: Finding value in markets that are expensive" by Guido Deboeck Viscovery SOMine is used to analyze stocks and find common patterns indicating good performance.
Kantardzic, M. (2011). 2nd edition. John Wiley & Sons, Inc.
This is an introductory book into the field of data mining. It discusses common methods for data cleansing and preprocessing, exploration, classification, prediction and visualization. It includes introductions to self-organizing maps and some statistical methods used in Viscovery products.
A short discussion of the Viscovery data mining suite version 5 can also be found.
Smith, K.A., & Gupta, J.N.D. (Eds.) (2001). IGI Global
This book briefly reviews the two main types of neural networks that are applied in business: multilayered feedforward neural networks and SOMs. Several use cases for these methods are discussed and guidelines are provided for facilitating the successful application of these neural network models to business problems. Critical guidelines for facilitating the successful application of neural network methods to business problems are provided.
In the introductory chapter, Viscovery SOMine is used to create a SOM of countries based on economic performance indicators.
In the chapter “Credit rating classification using self-organizing maps” Viscovery SOMine is used to cluster financial statement data for 300 American companies trading in consumer cyclicals, producing a good fit with Standard and Poor ratings and revealing that ratings are largely dependent on the financial indicators used.
Tan, J. (Ed.) (2010). IGI Global
This book discusses recent developments in healthcare IT systems. It covers topics such as medical online encyclopedias, decision support systems, patient satisfaction analyses, prediction of attendance rates in voluntary health programs, and more.
In the chapter "Towards Process-of-Care Aware Emergency Department Information Systems: A Clustering Approach to Activity Views Elicitation" by Andrzej S. Ceglowski and Leonid Churilov, Viscovery SOMine is used to create process-oriented clusters of patients in emergency departments, to provide the basis for optimized patient allocation and the prediction of time expenditure.
Salmen, S.M., Gröschl, M. (Eds.) (2004). Physica-Verlag Heidelberg
Customer analytics is a key issue for many Viscovery users. This book in German language covers basic concepts of electronic customer care and presents practical examples from various industries.
In the chapter "Self-Organizing Map-basiertes Customer Behaviour Modeling als Schlüssel zur digitalen Kundennähe" by Dorothea Heiss and Bernhard Kuchinka, Viscovery is used to study the buying behavior of 100,000 customers of a mail-order company.
Mena, J. (2012). CRC Press
This book discusses methods for web analytics and IT-based marketing. A variety of case studies give the reader an idea how he can benefit in his own field.
The Viscovery software is briefly discussed as a powerful representative of knowledge discovery tools.
Martin, W. (2015). S.A.R.L. Martin, Annecy, France
Modern Business Intelligence must respond to the challenges of quickly changing business processes and vast amounts of data. For agile, smart and data-driven organizations, performance management is needed for unerring monitoring and controlling of business processes, and analytics, in particular Big Data analytics, must improve competitiveness in extremely dynamic and volatile markets moving towards the Internet of Things.
Viscovery SOMine is presented as one of the preferred software tools for predictive analytics and data mining.
Deboeck, G., & Kohonen, T. (Eds.) (1998). Springer-Verlag London
This book looks at SOM applications in finance, economic, and marketing applications. The book contains various applications of unsupervised neural networks using Kohonen's self-organizing map approach.
The application of SOMs to the modeling and analysis of financial data is demonstrated in detail using Viscovery SOMine. Sample data sets describing mutual funds, emerging markets, and responses to a CEIBS questionnaire are used to analyze investment opportunities and credit risk and to uncover consumer attitudes in Beijing and Shanghai.
Sarlin, P. (2014). Springer-Verlag Berlin Heidelberg
The focus of this book is on creating models for risk identification and assessment in macroeconomic systems. Sarlin introduces his concept of self-organizing financial stability maps and discusses a general framework for similar applications.
Many of the SOM models in this book were created using Viscovery SOMine.
Moser, A.T. (2010). VDM Verlag
Artificial Intelligence methods are characterized by high predictive accuracy, but usually have the disadvantage of lack of transparency. Using self-organizing maps, the author shows that a degree of transparency is possible here as well. The book focuses on the development of models that are able to forecast insolvency. A method is presented that provides a quantitative indicator by calculating, testing and analyzing ensembles of nonlinear models and filtering out the most effective models.
Viscovery software is used to visualize corresponding scores and key figures and to derive profiles of the effects of these key figures.