Self-organizing maps have shown their suitability for analyzing financial data in a number of studies. They overcome the assumption on normality in the underlying distribution encountered when using multivariate statistical methods as well as difficulties in finding an appropriate functional form for the distributions. Moreover, the results are rather easy to visualize when there are several explanatory variables. Our aim in this study is to get further evidence of this method's suitability to analyze financial data. We show that it can be used to analyze financial performance both between companies in one period and in several periods. We anticipate that self-organizing maps can be used in future for comparing financial performance between different companies and between the same company over time.
[1]
Hannu Vanharanta,et al.
Validity and utility of a hyperknowledge-based financial benchmarking system
,
1995,
Proceedings of the Twenty-Eighth Annual Hawaii International Conference on System Sciences.
[2]
Kaisa Sere,et al.
Managing Complexity in Large Data Bases Using Self-Organizing Maps
,
1996
.
[3]
Hannu Vanharanta,et al.
Hyperknowledge and contitnuous strategy in executive support systems
,
1995
.
[4]
Teuvo Kohonen,et al.
Self-Organizing Maps
,
2010
.
[5]
Kaisa Sere,et al.
Competitive financial benchmarking using self-organizing maps
,
1997
.