Issue 1, 2005

Zherebtsov A. A., Kuperin Y. A. An Application of Selforganized Kohonen Maps to Clusterization of DJIA and NASDAQ 100 Indeces: Artificial Intelligence in Financial Management

In this paper we apply the Self-Organized Map (SOM) method for clustering Dow-Jones Industrial Average (DJIA) and NASDAQ 100 portfolios for determination of nonlinear correlations between stocks. We develop the application of this approach as alternative to ultrametric spaces method. We have found, that SOM method is more relevant flexible and perspective for clustering ill-structured large datasets.

<< Contents: Issue 1, 2005
<< Go to archive