Iraqi Stock Market Prediction Using Artificial Neural Network and Long Short-Term Memory

Abstract

Stock prediction is one of the most important issues on which the investor relies in building his investment decisions and the financial literature has relied heavily on predicting future events because of its exceptional importance in financial work, after which profit or loss is determined, and since money dealers are eager to profit, the researchers have devoted techniques to forecast as providing the tools to achieve this. The choice of the proper model of time series data affects the precision of the predictions, and stock market data is typically random and turbulent for various industries. To obtain forecast models of stock market data that can accurately portray reality and obtain future forecasts, these models must take all data considerations from linear and none linear trends, different influences, and other data factors, hence the research problem of obtaining a method that gives predictions of Iraq's stock market indicators that are accurate and reliable in stock analysis. In this paper, two models were proposed to predict the Iraqi stock markets index through the use of artificial neural networks (ANN) and a long short-term memory (LSTM) algorithm where Iraqi stock market data were used from 2017 to 2021 and good results were achieved in the prediction where the long short-term memory (LSTM) algorithm reached a mean square error (MSE) rate of as little as 0.0016 while the artificial neural network (ANN) algorithm reached error rate 0.0055.