A Comparative Analysis of Machine Learning Models for Long and Short-Term Forecasting of the Egyptian Stock Market: A Focus on EGX30

arXiv cs.AI · 6 hours ago

Researchers compared five machine learning models for predicting prices in the Egyptian EGX30 stock index using historical data and metrics like root mean squared error and mean absolute percentage error. Gated Recurrent Unit networks outperformed other models for one-week, one-month, and two-month predictions, while eXtreme Gradient Boosting performed best for one-day predictions; ensemble techniques achieved results 5 times better than GRU alone in two-month forecasting. The findings suggest different models suit different prediction timeframes, potentially helping Egyptian market investors make more informed trading decisions.