Predictive Analytics of Tesla and Google Stock Prices Using Advanced Machine Learning Frameworks
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Stock market forecasting remains a challenging task due to the nonlinear, volatile, and stochastic nature of financial time- series data. This study aims to (i) comparatively evaluate statistical and machine learning approaches for stock price prediction, (ii) assess the impact of technical feature engineering on forecasting accuracy, and (iii) analyze the suitability of different models for volatile technology-driven stocks. A comparative framework is developed using ARIMA, Prophet, and Random Forest regression to forecast the daily closing prices of Tesla and Google stocks. Historical price data are preprocessed and enriched with technical indicators, including moving averages, momentum indicators, and volatility measures. Model performance is evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2). Experimental results demonstrate that the Random Forest model consistently outperforms ARIMA and Prophet, achieving lower prediction errors due to its ability to capture nonlinear relationships through engineered features. ARIMA and Prophet serve as effective statistical baselines for trend and seasonal analysis. The findings confirm that feature-driven ensemble learning significantly enhances predictive accuracy, highlighting its applicability in algorithmic trading and decision-support systems.
Fields of Study & Subjects
Stock Market Forecasting Methods
Forecasting Techniques and Applications
Financial Markets and Investment Strategies
Publication details
- Journal / source
- International Conference on Intelligent Sustainable Systems (ICISS)
- Pages
- 1849–1856
- Publication date
- 4 March 2026
- Language
- EN