Multi-model ensemble deep learning framework for robust stock market forecasting: integration of economic indicators and temporal dependencies

Our research work investigates how ensemble based machine learning methods can enhance stock market forecasting. A novel framework named XML is introduced, integrating XGBoost, MLP, and LSTM models to achieve higher predictive accuracy in stock price prediction. We evaluated the performance of the model with various baseline machine learning algorithms, including neural networks, support vector machines, and random forests, to predict stock prices. The research utilizes historical stock price data, trading volume, and news sentiment analysis as input features for the models. The study evaluates the performance of the models using metrics such as Mean squared error (MSE), Mean Absolute Error (MAE), and R-Squared. This study seeks to explore how machine learning techniques can enhance stock price forecasting and supports the advancement of more precise and dependable predictive models within financial markets. Preliminary results indicate promising performance of the machine learning models in predicting stock prices.