The ability of an ant colony algorithm to predict the Stock Price Crash Risk

the stock price crash risk is an indicator for measuring risk asymmetry and is of great importance in analyzing portfolios and pricing asset holdings. Considering the importance of the risk of collapse, several studies have examined the effective factors on it, all of which use traditional methods of forecasting, while in recent years, new methods of hypermetricity have been widely used in other financial issues. It is used and has better results. Therefore, in this research, the risk of falling stock prices of listed companies in Tehran Stock Exchange is predicted using the Ant Colony Algorithm and the results with multivariate regression as a traditional method, compared. The statistical population of the study consisted of all companies listed on the stock exchange, with 101 companies selected as sample. Initially, 19 independent variables were introduced into the model as the input of the particle accumulation algorithm in this study. Finally, in each of the different criteria for calculating the stock price crash risk, some optimal variables were selected, then using An ant colony algorithm and multivariate regression, the stock price crash risk predictions and the resulting results were compared. In order to compare the methods, two criteria of mean absolute error and mean square error are used. The results show that the ability of the ant an algorithm to predict the stock price crash risk is higher than multivariate regression and the research hypothesis is confirmed.