Nationality and risk attitude: Testing differences and similarities of investors' behavior in selected financial markets

We first applied cluster analysis on selected stock market indexes (NASDAQ, DAX, Nikkei 225, FTSE 100, and Dow-Jones) for identifying four global fundamental patterns of stock markets behavior (to be named "market conditions"). On each of these patterns (attesting similar market conditions) we then applied Support Vector Machine (SVM) classification technique to test for the similarities and differences in the behavior of investors in the various stock markets. Our results show a good degree of separation of investors' behavior for the selected national stock markets (i.e., investors in different national financial markets react differently, facing the same market conditions, while the two US national markets (NASDAQ and Dow-Jones) behave the same). The results could be interpreted as a positive evidence for different investor behavior (and risk attitude) in different national stock markets. The presented approach could be used for further classification of financial indices behavior, and investment strategies associated with multinational investment portfolios.