Applying ensemble learning to multiple stock price predictions: A comparative study

Abstract

Predicting stock prices has been a perennial challenge and topic of interest for financial analysts, investors, and researchers alike. This holds true especially for influential tech companies that significantly impact the stock market landscape like Google and Tesla. While numerous models and methods have been applied to forecast stock prices globally, there remains a gap in a comparative, in-depth evaluation using Support Vector Regression (SVR), Recurrent Neural Network (RNN), Long Short-Term Memory network (LSTM), and XGBoost models for predicting prices of prominent tech stocks. This paper aims to bridge this gap, presenting a comprehensive model comparison for stock price forecasting. A series of datasets, inclusive of Google's stock prices and Tesla stock price, form the backbone of the analysis. Among the evaluated models, our preliminary findings indicate that LSTM and XGBoost demonstrate superior predictive capabilities, capturing intricate market dynamics with high precision. Further, the paper delves into the underlying factors and patterns driving stock prices, gleaning insights from the models' predictions. Through this research, this paper offers valuable benchmarks and insights for the best model for research in the field of stock price predictions and some evaluation of different features in the field of stock price predictions.