Ploutos: Towards interpretable stock movement prediction with financial large language model

TL;DR

Ploutos introduces a novel financial large language model framework that effectively fuses textual and numerical data for stock prediction, providing interpretable rationales and outperforming existing methods.

Contribution

The paper presents Ploutos, a new framework combining multiple experts and GPT-based models to enhance interpretability and accuracy in stock movement prediction.

Findings

Outperforms state-of-the-art methods in prediction accuracy

Provides interpretable rationales for predictions

Effectively fuses textual and numerical data

Abstract

Recent advancements in large language models (LLMs) have opened new pathways for many domains. However, the full potential of LLMs in financial investments remains largely untapped. There are two main challenges for typical deep learning-based methods for quantitative finance. First, they struggle to fuse textual and numerical information flexibly for stock movement prediction. Second, traditional methods lack clarity and interpretability, which impedes their application in scenarios where the justification for predictions is essential. To solve the above challenges, we propose Ploutos, a novel financial LLM framework that consists of PloutosGen and PloutosGPT. The PloutosGen contains multiple primary experts that can analyze different modal data, such as text and numbers, and provide quantitative strategies from different perspectives. Then PloutosGPT combines their insights and predictions and generates interpretable rationales. To generate accurate and faithful rationales, the training strategy of PloutosGPT leverage rearview-mirror prompting mechanism to guide GPT-4 to generate rationales, and a dynamic token weighting mechanism to finetune LLM by increasing key tokens weight. Extensive experiments show our framework outperforms the state-of-the-art methods on both prediction accuracy and interpretability.