Application of Kohonen SOM Learning in Crisis Prediction
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F17%3A00316545" target="_blank" >RIV/68407700:21340/17:00316545 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Application of Kohonen SOM Learning in Crisis Prediction
Original language description
The Self-Organized Mapping (SOM) is a traditional tool for multidimensional data analysis which overperforms analytical power of cluster analysis. But there are possible difficulties when the SOM is applied to data patterns of large size. Our approach macro-economical data analysis is based on logarithmic differences, pattern dimensionality reduction and finalization of data analysis using Kohonen SOM learning. This general methodology was applied to the statistic data describing the economic situation of thirty five countries during more than twenty years. The regularly published data come from statistics of European Commission. The aim is to identify similar groups of countries and characterized the similarity. The role of SOMtopology, learning strategy and reduced pattern size can be also used to crisis prediction based on similarities with countries already suffering with crisis.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Mathematical Methods in Economics MME 2017
ISBN
978-80-7435-678-0
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
254-258
Publisher name
Univerzita Hradec Králové
Place of publication
Hradec Králové
Event location
Hradec Králové
Event date
Sep 13, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—