Abstract:
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 prediction and modeling of 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 not any 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.
Machine summary:
Predicting Stock Market Crashes Using Self-Organizing Neural Networks Self-Organizing Arash Mohammadali Zadeh 1, Reza Ra'i 2, Shahpour Mohammadi 3 A market crash is a phenomenon that leads to the loss of wealth and assets of investors over a relatively short period of time.
An overview of theories and models presented for predicting crashes in the stock market shows that there is no consensus among researchers regarding observed patterns of variables such as trading volume, returns, volatility, fundamental factors, behavioral indicators, etc.
In this research, using self-organizing neural networks, a method is presented for predicting crashes in the Iranian stock market.
Prediction, Stock Market Crash, Neural Networks, Self-Organizing Mapping 1.
In any case, it can be said that a market crash occurs when a significant number of stocks in the market experience a sharp and one-time price drop, which can be caused by changes in fundamental market factors or public panic4 (Garber, 1992).
The first category of models explains and predicts stock market crashes based on changes in external information about fundamental market factors.
An overall review of the theories and models presented for predicting crashes in the stock market shows that there is no consensus among researchers regarding the observed patterns of variables, such as trading volume, returns, volatility, fundamental factors, behavioral indicators, etc.
This research attempts to use self-organizing mapping neural networks to devise a method for predicting crashes in the Iranian stock market.
Hong and Stein, based on differences in investor views, presented a model for stock market crashes and stated that significant price changes can occur without important news in fundamental factors.
(
, 
, 
)
