Forecasting stock prices remains a considerable challenge in financial markets, bearing significant implications for investors, traders, and financial institutions. Amid the ongoing AI revolution, NVIDIA has emerged as a key player driving innovation across various sectors. Given its impact, we chose NVIDIA as the subject of our study. We evaluate the effectiveness of four different forecasting models on NVIDIA’s next day stock prices: Autoregressive Integrated Moving Average (ARIMA), Multilayer Perceptron Network (MLP), Long Short-Term Memory (LSTM) networks, and ARIMA integrated with the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model. Utilizing data sourced from Yahoo Finance’s API over a five-year period from 2019 to 2024, our findings indicate that the ARIMA-GARCH model outperforms the others in terms of Root Mean Square Error (RMSE) for predicting NVIDIA’s next day stock prices. This result suggests that combining volatility modeling with other forecasting techniques can potentially enhance accuracy in volatile markets.