Stock Price Prediction Through Multifaceted Data Integration and Machine Learning

This work addresses the challenge of predicting stock prices by proposing a machine learning (ML) model that integrates Independent Component Analysis (ICA) for feature selection and Random Forest (RF) for predicting closing stock prices. The model is evaluated on S&P500 and S&P100 datasets from February 8, 2022, to February 6, 2023. Preprocessing involves normalizing data and applying technical indicators to extract features. The ICA-RF model undergoes evaluation using metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R2. This approach aims to enhance predictive capabilities in stock market forecasting.