Forecasting NVIDIA’s Stock with AI: A Study of Predictive Models
Evaluating the Performance of ARIMA, LSTM, MLP, and ARIMA-GARCH Models Over Five Years
Financial institutions and investors both need to be able to predict the future price of a stock. As artificial intelligence advances, NVIDIA has become a key player in machine learning fields due to its advances in artificial intelligence. Therefore, we focus on NVIDIA in our article. Among the models we are using are ARIMA, MLP, LSTM, and a combined ARIMA-GARCH model.
Based on data from Yahoo Finance, I have analyzed NVIDIA stocks performance from April 12 2019 to April 11 2024. According to the results, the ARIMA-GARCH model has the lowest RSME for predicting the stock price, which is better than expected. Mixing volatility modelling with other methods improves prediction accuracy in the overall predictable stock market, according to the findings.
Introduction
Feature engineering and a specialized model are two of the things Shen, J., and Shafiq, M.O. have combined to develop a deep learning technique. For predicting stock trends, their model outperforms traditional models.
Yakup Kara, Melek Acar Boyacioglu, and Ömer Kaan Baykan developed artificial neural networks (ANNs) and support vector machines (SVMs) to predict the Istanbul Stock Exchange National 100 Index. An ANN showed 75.74% accuracy compared to 71.52% for an SVM.
