Leveraging Large Language Models for Sentiment Analysis and Investment Strategy Development in Financial Markets

This study investigates the application of large language models (LLMs) in sentiment analysis of financial news and their use in developing effective investment strategies. We conducted sentiment analysis on news articles related to the top 30 companies listed on Nasdaq using both discriminative models such as BERT and FinBERT, and generative models including Llama 3.1, Mistral, and Gemma 2. To enhance the robustness of the analysis, advanced prompting techniques—such as Chain of Thought (CoT), Super In-Context Learning (SuperICL), and Bootstrapping—were applied to generative LLMs. The results demonstrate that long strategies generally yield superior portfolio performance compared to short and long–short strategies. Notably, generative LLMs outperformed discriminative models in this context. We also found that the application of SuperICL to generative LLMs led to significant performance improvements, with further enhancements noted when both SuperICL and Bootstrapping were applied together. These findings highlight the profitability and stability of the proposed approach. Additionally, this study examines the explainability of LLMs by identifying critical data considerations and potential risks associated with their use. The research highlights the potential of integrating LLMs into financial strategy development to provide a data-driven foundation for informed decision-making in financial markets.