The issue of feature selection is one of the important issues in machine learning, which is very important in many applications, because there are many features in these applications, many of which are either unused or lacking a lot of information. Not removing these features will increase the amount of computation. This issue is also important in financial discussions, especially in matters relating to capital market forecasting. One of the important issues in the stock market is the stock price crash risk Which has many factors affecting it, Therefore, identification of optimal variables in this case is very important. The purpose of this study is to identify the optimal variables in predicting the stock price crash risk, using the combination of genetic algorithm and artificial neural network as a feature selection method. The results show that among the 14 independent variables, 7 variables were selected as optimal variables, all of which, according to previous studies, have the ability to predict the stock price crash risk.
