Stock Price Prediction Using EGARCH Model and Fusion of Neural Network with Culture Algorithms

AI Algorithms are one of the most powerful tools for data analysis and modeling of non-linear equations that have widely been used in the analysis of stock market in recent years. In this paper, we will demonstrate the performance of fusion evolutionary Algorithms and Autoregressive Conditional Heteroskedasticity of models like EGARCH as a new method to predict the stock market. Comparing the efficiency of this method with similar ones for South Korean stock prices, the efficiency of the new model for stock market predictions will be investigated compared with previous works. Results show that the combination of Autoregressive Conditional Heteroskedasticity models with evolutionary algorithms are improved and are more efficient in forecasting stock.