Where academic tradition
meets the exciting future

You are here: TUCS > PUBLICATIONS > Publication Search > A Visualization and Clustering...

A Visualization and Clustering Approach to Analyzing the Early Warning Signals of Currency Crises

Shuhua Liu, Tomas Eklund, Mikael Collan, Peter Sarlin, A Visualization and Clustering Approach to Analyzing the Early Warning Signals of Currency Crises. In: Jue Wang, Shouyang Wang (Eds.), Business Intelligence in Economic Forecasting: Technologies and Techniques, 65–81, IGI Global, 2010.

Abstract:

In this chapter, we investigate the use of advanced machine learning and data analysis methods for analyzing the early warning signals of currency crisis. So far the empirical studies on economic crises have focused on conventional economic modeling methods. Our study aims to see if new insights can be gained from the application of other methods, more specifically neural network based clustering analysis methods such as the SOM (Self-Organizing Maps), in analyzing important economic indicators for the prediction of financial crises. We shall first give a review of studies on crisis early warning systems, introduce the SOM method, then present and discuss the results from analyzing the 1992 Finnish currency crisis using the SOM.

BibTeX entry:

@INBOOK{cLiEkCoSa10a,
  title = {A Visualization and Clustering Approach to Analyzing the Early Warning Signals of Currency Crises},
  booktitle = {Business Intelligence in Economic Forecasting: Technologies and Techniques},
  author = {Liu, Shuhua and Eklund, Tomas and Collan, Mikael and Sarlin, Peter},
  editor = {Wang, Jue and Wang, Shouyang},
  publisher = {IGI Global},
  pages = {65–81},
  year = {2010},
  keywords = {financial crisis, early warning, clustering analysis, self-organizing maps},
}

Belongs to TUCS Research Unit(s): Data Mining and Knowledge Management Laboratory

Publication Forum rating of this publication: level 1

Edit publication