prediction of stock market crash using self-organizing maps

market crash is a phenomenon which occurs in stock markets occasionally and leads to loss of the investors’ wealth and assets in a relatively short period of time. therefore, attempts for prediction of this phenomenon are of much importance for the investors, financial institutions and government. to this date, numerous and varied studies have been carried out for predicting and modeling  stock markets and their crash. each of these studies has tried to fulfill this important task more precisely from a different point of view. a brief review of the theories and models presented for prediction of stock market crash indicates that there is no agreement among the researchers in relation to the observed patterns of variables such as trading volume, returns, volatility, fundamental factors, behavioral indicators, etc. in the stock markets in the pre-crash period. one of the very suitable methods proposed for finding the existing patterns in the data is the self-organizing map neural networks method which is considered as a non-parametric and non-linear method. in this study, a method is proposed for prediction of the crash in the iranian stock market using the self-organizing map neural networks. the results of implementation of the model and out-of-sample prediction indicate that the model has a relatively acceptable performance in prediction of the pre-crash periods in the stock market.