Guido J Deboeck

• PhD Economics
• Consultant at World Bank

This article summarizes "best practices" in data mining, clustering and visualization of large multi-dimensional data sets in finance, economics or marketing. These best practices are based on the lessons learned from many applications presented in Visual Explorations in Finance with self-organizing maps (Springer-Verlag, 1998), lessons extracted f...

Applications of neural networks to finance and investments can be found in several books and articles. The great majority of these applications use supervised neural network models for forecasting market trends, creating trading models, portfolio or risk management. So far few applications of unsupervised neural networks in finance are documented i...

This article provides a brief overview of the motivations, the methodology, and some of the applications elaborated in Visual Explorations in Finance

Picking stocks that are suitable for portfolio management is a complex task. The most common criteria are the price earnings ratio, the price book ratio, price sales ratio, the price cash flow ratio, and market capitalization. Another approach called CAN SLIM relies on earnings growth (quarterly and annual earnings growth) of companies; the relativ...

Electronic direct access trading often simply called day trading has exploded in popularity at the end of the 20th century. The increased interest in short-term trading and the approaches are analyzed and some intra-day trading strategies and how they can be deployed in practice, are discussed.

Based on traditional measures of value such as price-earnings ratio (PE) many stocks are at present either overvalued or are faring very poorly. The rapid expansion of Internet and technology companies has made surfing stock markets much more hazardous. The main idea of this chapter is to demonstrate how maps can be designed for finding value in st...

From the Publisher: SOMs (Self-Organizing Maps) have proven to be an effective methodology for analyzing problems in finance and economics--including applications such as market analysis, financial statement analysis, prediction of bankruptcies, interest rates, and stock indices. This book covers real-world financial applications of neural networks...

The focus in this chapter is better understanding of the trends and patterns among today’s emerging markets. About 80 countries currently have functioning securities exchanges. Based on the emerging stock market data published by the International Finance Corporation (IFC), this chapter analyzes patterns across emerging markets and patterns in the...

Data analysis, clustering and visualization with SOM is commonly done with (a) public domain software, (b) self-coded software or (c) commercial software packages. In particular, there is an increasing number of commercial, off-the-shelf, user-friendly software tools that are becoming more and more sophisticated. This chapter contains a brief overv...

This chapter summarizes best practices in data mining and visual data explorations through clustering of multi-dimensional data in finance, economics and marketing. The best practices outlined in this chapter are based on (i) the lessons learned from all the chapters in this book, (ii) lessons learned from other papers not included here, (iii) the...

Market research and consumer segmentation is still in its infancy in the People’s Republic of China. Yet, marketers desperately need information about differential response patterns and consumer segments to formulate viable strategies for the drastically growing Chinese consumer market. This chapter presents the results of consumer surveys with hun...

The self-organizing map approach can be used to translate multi-dimensional mutual fund data into simple two-dimensional maps. These maps provide a significant improvement over the information that is traditionally published on mutual funds. They create a better basis for portfolio selection, for comparison of the performance of mutual funds and fo...

The author focuses on advanced technology and its impact on financial markets. The author provides an overview of case studies and findings about fractal market analysis of financial markets, use of neural networks for trading and stock selection, the use of genetic algorithms for optimization of trading strategies, applications of fuzzy logic for...

This publication was never available in electronic format. It may possibly be accessed via World Bank archives.

Part I of this article outline twelve steps for data processing of large multi-dimensional data set using unsupervised neural network or self-organizing map (SOM) approach. These steps will be applied to assessing the risks involved in investing in various stock markets around the world. This application is based on a data set containing financial,...

this article we focus on one class of neural networksand within that class on one single approach, i.e. the self-organizing mapapproach (SOM). This approach invented by Teuvo Kohonen has beenaround since the early 1980's and has since been used extensively inengineering and other technical fields. Recently self-organizing mapshave also been used in...