Machine Learning Models-Based Forecasting Moroccan Stock Market

This paper explores the critical domain of finance research by focusing on modeling and forecasting daily prices for the Moroccan All Shares Index (MASI) across diverse sectors. Recognizing the pivotal role of predicting stock price movements in shaping investment strategies, we conduct a comprehensive comparative study employing various Machine Learning (ML) methods, including eXtreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), Multilayer Perceptron (MLP), SVR-XGBoost, MLP-XGBoost, and LSTM-XGBoost models. Leveraging an optimized Grid Search (GS) algorithm, our results highlight the superior performance of SVR-XGBoost and LSTM-XGBoost models, emphasizing their efficacy and accuracy in predicting daily prices for the MASI.