Stock Bubbles´ Nature: A Cluster Analysis of Chinese Shanghai a Share Based on SOM Neural Network

The stock market bubbles present different properties in different economic environments and stages, and their impacts on the economic system are varied. In this paper, self organizing map (SOM) and principal component analysis (PCA) were employed to determine the property of the stock bubbles in Shanghai stock market from Jan-2000 to Apr-2008. The nature of the bubbles was interpreted by factor analysis from the aspects of macroeconomic, stock marketpsilas speculative intensity and dilatation. The factors analyses of bubbles explained the bubblespsila nature by the characters of macroeconomic, stock market speculative intensity and expansion. The outcome demonstrates that SOM may help to determine the property of the bubbles in stock market.