Assessing early warning signals of currency crises: a fuzzy clustering approach

In the period of 1990s alone, four waves of financial crises occurred around the world. The repeated occurrence of financial crises stimulated a large number of theoretical and empirical studies on the phenomena, in particular studies on the determinants of or early warning signals of financial crises. Nonetheless, the different studies of early warning systems have achieved mixed results and there remains much room for further investigation. Since, so far, the empirical studies have focused on conventional economic modelling methods such as simplified probabilistic models and regression models, in this study we examine whether new insights can be gained from the application of the fuzzy clustering method. The theories of fuzzy sets and fuzzy logic offer us the means to deal with uncertainties inherent in a wide variety of tasks, especially when the uncertainty is not the result of randomness but the result of unknown factors and relationships that are difficult to explain. They also provide us with the instruments to treat vague and imprecise linguistic values and to model nonlinear relationships. This paper presents empirical results from analysing the Finnish currency crisis in 1992 using the fuzzy C‐means clustering method. We first provide the relevant background knowledge and introduce the fuzzy clustering method. We then show how the use of fuzzy C‐means method can help us to identify the critical levels of important economic indicators for predicting of financial crises. Copyright © 2007 John Wiley & Sons, Ltd.