Visual Explorations in Finance

by Deboeck, Guido J.; Kohonen, Teuvo

• ISBN13: 9783540762669
• ISBN10: 3540762663
• Format: Hardcover
• Copyright: 1998-08-01
• Publisher: Springer Verlag

Summary

Self-organizing maps (SOM) have proven to be of significant economic value in the areas of finance, economic and marketing applications. As a result, this area is rapidly becoming a non-academic technology. This book looks at near state-of-the-art SOM applications in the above areas, and is a multi-authored volume, edited by Guido Deboeck, a leading exponent in the use of computational methods in financial and economic forecasting, and by the originator of SOM, Teuvo Kohonen. The book contains chapters on applications of unsupervised neural networks using Kohonen's self-organizing map approach.

Table of Contents

Contributing Authors	xix	(6)
Introduction	xxv
Knowledge Discovery	xxv	(4)
Exploratory Data Analysis and Data Mining	xxix	(1)
Traditional Methods	xxx	(4)
Self-Organizing Maps	xxxiv	(2)
Simple Example: Mapping Scotch Whiskies	xxxvi	(4)
Overview	xl
Part 1: Applications	3	(156)
1 Let Financial Data Speak for Themselves	3	(21)
Carlos Serrano-Cinca
1.1 Initial Analysis of Financial Data	3	(1)
1.2 SOM as a Tool for Initial Data Analysis	4	(14)
1.3 Integrating SOM into a Decision-Support System	18	(6)
2 Projection of Long-term Interest Rates with Maps	24	(15)
Eric de Bodt
Philippe Gregoire
Marie Cottrell
2.1 Introduction	24	(2)
2.2 Building Blocks	26	(2)
2.3 Simulating Future Behavior using Historical Information	28	(1)
2.4 Application	28	(7)
2.5 Validation	35	(1)
2.6 Extension to Value-at-Risk	36	(2)
2.7 Conclusions	38	(1)
3 Picking Mutual Funds with Self-Organizing Maps	39	(20)
Guido Deboeck
3.1 Exploratory Data Analysis	39	(1)
3.2 Morningstar Mutual Fund Database	40	(1)
3.3 A Simple Binary Example	40	(5)
3.4 Mapping Mutual Funds	45	(12)
3.5 Conclusions	57	(2)
4 Maps for Analyzing Failures of Small and Medium-sized Enterprises	59	(13)
Kimmo Kiviluoto
Pentti Bergius
4.1 Corporate Failure--Causes and Symptoms	59	(2)
4.2 Self-Organizing Map as a Tool for Financial Statement Analysis	61	(1)
4.3 The Data	62	(1)
4.4 Results	63	(8)
4.5 Summary	71	(1)
5 Self-Organizing Atlas of Russian Banks	72	(11)
Serge Shumsky
A.V. Yarovoy
5.1 Introduction	72	(1)
5.2 Overview of the Russian Banking System	73	(2)
5.3 Problem Formulation	75	(1)
5.4 Linear Analysis using PCA	75	(1)
5.5 Nonlinear Analysis or the Nonlinear PCA Extension	76	(1)
5.6 SOM of Russian Banks	77	(2)
5.7 A SOM Atlas of Russian Banks in 1994	79	(2)
5.8 Evolution of Russian Banking from 1994 to 1995	81	(1)
5.9 Conclusions	81	(2)
6 Investment Maps of Emerging Markets	83	(23)
Guido Deboeck
6.1 Background	83	(1)
6.2 Performance and Risks of Investing in Emerging Markets	84	(2)
6.3 Patterns Among Emerging Markets	86	(15)
6.4 Strategic Implications of SOM for Investments in Emerging Markets	101	(4)
6.5 Conclusions	105	(1)
Color Plate Section follows Chapter 6
7 A Hybrid Neural Network System for Trading Financial Markets	106	(11)
Marina Resta
7.1 Introduction	106	(1)
7.2 ISOG: Integrated Self-Organization and Genetics	107	(2)
7.3 Simulation Results	109	(7)
7.4 Conclusions	116	(1)
8 Real Estate Investment Appraisal of Land Properties using SOM	117	(11)
Eero Carlson
8.1 Introduction	117	(1)
8.2 Geographic Information Systems	118	(1)
8.3 Visualization	119	(2)
8.4 Scaling	121	(1)
8.5 Sensitivity Analysis	122	(1)
8.6 Portfolio Computation	123	(1)
8.7 Adaptation to New Observations	124	(1)
8.8 Other Examples	124	(3)
8.9 Conclusion	127	(1)
9 Real Estate Investment Appraisal of Building using SOM	128	(13)
Anna Tulkki
9.1 Characteristic Features of the Finnish Real Estate Market	128	(1)
9.2 The Data	129	(1)
9.3 Preprocessing of the Data and the Research Method	129	(2)
9.4 The Results	131	(1)
9.5 Component Planes of the Map	131	(4)
9.6 Conclusions	135	(6)
10 Differential Patterns in Consumer Purchase Preferences using Self-Organizing Maps: A Case Study of China	141	(18)
Bernd Schmitt
Guido Deboeck
10.1 Introduction	141	(1)
10.2 What do we Know about Chinese Consumers?	142	(1)
10.3 A Selective Review of the Prior Segmentation Research	143	(1)
10.4 The CEIBS Survey	144	(1)
10.5 Methodology	144	(2)
10.6 Major Results	146	(10)
10.7 Conclusions	156	(3)
Part 2: Methodology, Tools and Techniques	159	(71)
11 The SOM Methodology	159	(9)
Teuvo Kohonen
11.1 Regression Principles	159	(1)
11.2 "Intelligent" Curve Fitting	160	(3)
11.3 The Self-Organizing Map Algorithm	163	(2)
11.4 The Neural Network Model of the SOM	165	(1)
11.5 Labeling the Neurons	166	(1)
11.6 The Batch Version of the SOM	167	(1)
11.7 Conclusion	167	(1)
12 Self-Organizing Maps of Large Document Collections	168	(11)
Timo Honkela
Krista Lagus
Samuel Kaski
12.1 Introduction	168	(1)
12.2 WEBSOM for Document Map Applications	169	(6)
12.3 Document Map Creation	175	(3)
12.4 Conclusions	178	(1)
13 Software Tools for Self-Organizing Maps	179	(16)
Guido Deboeck
13.1 Overview of Available Tools	179	(2)
13.2 SOM_PAK: The SOM Program Package	181	(3)
13.3 SOM: a MatLab Toolbox	184	(3)
13.4 Viscovery SOMine Lite: User-Friendly SOM at the Edge of Visualization	187	(4)
13.5 Appendix: Overview of Commercially Available Software Tools for Applying SOM	191	(4)
14 Tips for Processing and Color-coding of Self-Organizing Maps	195	(8)
Samuel Kaski
Teuvo Kohonen
14.1 The SOM Array	195	(1)
14.2 Scaling the Input Variables	196	(1)
14.3 Initialization of the Algorithm	196	(1)
14.4 Selection of the Neighbourhood Function and Learning Rate	196	(1)
14.5 Automatic Color-coding of Self-Organizing Maps	197	(6)
15 Best Practices in Data Mining using Self-Organizing Maps	203	(27)
Guido Deboeck
Main Steps in using Self-Organizing Maps	203	(9)
Sample Application on Country Credit Risk Analysis	212	(17)
Conclusions	229	(1)
Notes	230	(3)
Glossary	233	(9)
Bibliography	242	(8)
Subject Index	250	(5)
Author Index	255	(2)
Website Index	257