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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Haojie, Lin, Zihan, Rojas, Randall R.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913939710803968
author Liu, Haojie
Lin, Zihan
Rojas, Randall R.
author_facet Liu, Haojie
Lin, Zihan
Rojas, Randall R.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09739
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Trading Performance Through Sentiment Analysis with Large Language Models: Evidence from the S&P 500
Liu, Haojie
Lin, Zihan
Rojas, Randall R.
Computational Finance
Trading and Market Microstructure
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.
title Enhancing Trading Performance Through Sentiment Analysis with Large Language Models: Evidence from the S&P 500
topic Computational Finance
Trading and Market Microstructure
url https://arxiv.org/abs/2507.09739