Enhancing Trading Performance Through Sentiment Analysis with Large Language Models: Evidence from the S&P 500

TL;DR

This paper demonstrates that integrating real-time sentiment analysis from financial news using large language models with traditional technical indicators enhances trading strategies for the S&P 500, especially in volatile markets.

Contribution

It introduces a novel approach combining GPT-2 and FinBERT sentiment analysis with technical and time-series models to improve stock trading performance.

Findings

Sentiment integration improves trading returns.

Combining models outperforms benchmark strategies.

Enhanced adaptability in volatile markets.

Abstract

This study integrates real-time sentiment analysis from financial news, GPT-2 and FinBERT, with technical indicators and time-series models like ARIMA and ETS to optimize S&P 500 trading strategies. By merging sentiment data with momentum and trend-based metrics, including a benchmark buy-and-hold and sentiment-based approach, is evaluated through assets values and returns. Results show that combining sentiment-driven insights with traditional models improves trading performance, offering a more dynamic approach to stock trading that adapts to market changes in volatile environments.