NVIDIA Stock Price Prediction by Machine Learning

Abstract

This study explores how to forecast NVIDIA stock values using machine learning models. The chosen prediction models are Long Short-Term Memory (LSTM), Random Forest, and Linear Regression. Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R² score are only a few of the metrics used to assess the effectiveness of a model. The empirical findings showcase the remarkable prowess of the LSTM model in prognosticating NVIDIA stock prices, exhibiting a heightened level of accuracy and predictive acumen in contrast to Random Forest and Linear Regression counterparts. This investigation not only contributes a potent methodology to the realm of stock market prognostication but also holds promising prospects for prospective real-world implementations. Future implications include enhancing decision-making for investors and promoting financial stability through accurate market trend assessment.