Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?
Study evaluates LLMs' ability to predict Chinese stock prices using sentiment analysis from financial news texts.
What it examines
This paper explores the potential of Large Language Models (LLMs) to enhance quantitative trading strategies by extracting sentiment factors from Chinese financial news. It aims to evaluate the performance of different LLMs in this context using a standardized experimental procedure and back-testing framework.
What it concludes
The research demonstrates that language-specific pre-training can significantly enhance the performance of LLMs in extracting sentiment factors from Chinese financial news. This has potential applications in developing more effective quantitative trading strategies. Future research could explore further fine-tuning and pre-training techniques.
Evidence objects
The research demonstrates that language-specific pre-training can significantly enhance the performance of LLMs in extracting sentiment factors from Chinese financial news. This has potential applications in developing more effective quantitative trading strategies. Future research could explore further fine-tuning and pre-training techniques.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Abstract: The rapid advancement of Large Language Models (LLMs) has spurred discussions about their potential to enhance quantitative trading strategies. LLMs excel in analyzing sentiments about listed companies from financial news, providing critical insights for trading decisions. However, the performance of LLMs in this task varies substantially due to their inherent characteristics. This paper introduce… ▽ More The rapid advancement of Large Language Models (LLMs) has spurred discussions about their potential to enhance quantitative trading strategies. LLMs excel in analyzing sentiments about listed companies from financial news, providing critical insights for trading decisions. However, the performance of LLMs in this task varies substantially due to their inherent characteristics. This paper introduces a standardized experimental procedure for comprehensive evaluations. We detail the methodology using three distinct LLMs, each embodying a unique approach to performance enhancement, applied specifically to the task of sentiment factor extraction from large volumes of Chinese news summaries. Subsequently, we develop quantitative trading strategies using these sentiment factors and conduct back-tests in realistic scenarios. Our results will offer perspectives about the performances of Large Language Models applied to extracting sentiments from Chinese news texts. △ Less
Source row: 2107 · abstract type: unknown