Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models
SEP framework uses self-reflective LLMs and PPO to generate explainable stock predictions, outperforming traditional methods.
What it examines
The paper proposes the Summarize-Explain-Predict (SEP) framework to generate explainable stock predictions using self-reflective large language models (LLMs) and Proximal Policy Optimization (PPO). It aims to address the challenges of chaotic social texts and the need for expert-annotated explanations.
What it concludes
The SEP framework enhances explainable stock predictions and portfolio construction, with potential applications in financial analysis and investment strategies. Future research could focus on increasing robustness and incorporating additional data sources. The study's limitations include potential cumulative errors in the SEP process.
Evidence objects
The SEP framework enhances explainable stock predictions and portfolio construction, with potential applications in financial analysis and investment strategies. Future research could focus on increasing robustness and incorporating additional data sources. The study's limitations include potential cumulative errors in the SEP process.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Abstract: Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of s… ▽ More Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important than the others. On the other hand, to fine-tune LLMs for such a task, one would need expert-annotated samples of explanation for every stock movement in the training set, which is expensive and impractical to scale. To tackle these issues, we propose our Summarize-Explain-Predict (SEP) framework, which utilizes a self-reflective agent and Proximal Policy Optimization (PPO) to let a LLM teach itself how to generate explainable stock predictions in a fully autonomous manner. The reflective agent learns how to explain past stock movements through self-reasoning, while the PPO trainer trains the model to generate the most likely explanations from input texts. The training samples for the PPO trainer are also the responses generated during the reflective process, which eliminates the need for human annotators. Using our SEP framework, we fine-tune a LLM that can outperform both traditional deep-learning and LLM methods in prediction accuracy and Matthews correlation coefficient for the stock classification task. To justify the generalization capability of our framework, we further test it on the portfolio construction task, and demonstrate its effectiveness through various portfolio metrics. △ Less
Source row: 1190 · abstract type: unknown