Predicting NVIDIA's Next-Day Stock Price: A Comparative Analysis of LSTM, MLP, ARIMA, and ARIMA-GARCH Models

TL;DR

This paper compares LSTM, MLP, ARIMA, and ARIMA-GARCH models to predict NVIDIA's next-day stock price, highlighting the strengths and limitations of each approach in financial forecasting.

Contribution

It provides a comprehensive comparative analysis of multiple models specifically applied to NVIDIA's stock, offering insights into their predictive performance.

Findings

LSTM outperforms other models in accuracy

ARIMA-GARCH captures volatility better

MLP shows moderate predictive capability

Abstract

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 prominence, we chose NVIDIA as the subject of our study.