Unveiling market dynamics: a machine and deep learning approach to Egyptian stock prediction

Abstract

Abstract Accurate stock price forecasting is essential for making smart investing choices. In the context of the Egyptian stock market, this study examines the predictive capabilities of several machine learning and deep learning models for stock price prediction. Five different datasets with historical stock price information from significant Egyptian companies are used in the study methods such as Random Forest, Linear Regression, LSTM, and Bi-LSTM which were employed and evaluated using performance metrics including Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-Squared. Among these, the Bi-LSTM model consistently delivered the most accurate price forecasts due to its superior ability to capture complex patterns and relationships inherent in stock market data. Additionally, statistical models ARIMA and GARCH were implemented for comparative purposes, but the machine learning and deep learning models outperformed these traditional approaches. This study contributes to a deeper understanding of stock price behavior in the Egyptian market, providing valuable insights for financial analysts and investors.