Enhancing Stock Price Prediction: A Hybrid Approach Leveraging Large Language Models and Deep Learning

Abstract

Accurate stock price prediction is a challenging yet crucial goal in finance, with significant implications for investment decisions and risk management. This paper presents a comprehensive review of machine learning techniques for stock price prediction, examining traditional methods such as regression and ensemble models, as well as advanced approaches that integrate sentiment analysis and textual data sources. With the emergence of powerful Large Language Models (LLMs) such as ChatGPT, Llama and Gemini, we explore their potential for enhancing predictive accuracy using historical stock data. Key challenges are discussed, including data quality, model interpretability, and adapting to dynamic market conditions. Additionally, this paper proposes a trustworthy stock price prediction model based on LLMs enabling informed investment decision-making. Experimental results demonstrate that ChatGPT-4o model achieved a prediction accuracy of approximately 97%, which can be improved by tuning model parameters. Consequently, the paper highlights the potential of LLMs in improving stock price forecasting.