نوع مقاله : مقاله پژوهشی
عنوان مقاله English
نویسندگان English
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 has been used and has had better results. The purpose of this research is to model the stock price crash risk of listed companies in Tehran Stock Exchange using the genetic algorithm and compare the results with logistic regression. For this purpose, a hypothesis was developed for the study of this issue and the data of 107 Tehran Stock Exchange listed companies for the period of 2010-2010 were analyzed. First, 14 independent variables were introduced as inputs of the combined genetic algorithm and artificial neural network, which was considered as a feature selection method, and 7 optimal variables were selected. Then, using genetic algorithm and logistic regression, predicted risk Stock price collapse. The risk of falling stock prices has been used to measure the risk period. The results of this study indicate that a genetic algorithm based model is more capable of predicting the stock price crash risk than logistic regression. Therefore, the research hypothesis is confirmed.
کلیدواژهها English
Armano, G., marchesi, A., & Murru, A. (2005). "A hybrid genetic-neural architecture for stock indexes forecasting". Information sciences, ,3)33(.