用新闻+大模型预测多只股票，误差降7.11%。
Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion
- 用大模型处理新闻，通过股票名嵌入筛选相关资讯。
- 在多股票上训练统一模型，比单只股票方法降低7.11%误差。
- 适合想用新闻提升预测能力的量化研究者或从业者。
股票价格预测在金融预测中面临挑战。尽管传统方法如ARIMA和RNN广泛应用，但大型语言模型（LLMs）提供了新思路。本文提出一种融合预训练大模型与每日财经新闻的股价预测方法。为解决新闻数据处理及关键内容识别问题，我们在注意力机制中引入股票名称嵌入。具体地，使用预训练大模型编码新闻文章，并采用三种基于注意力的池化技术——自注意力、交叉注意力和位置感知自注意力池化——根据股票相关性筛选新闻。筛选后的新闻嵌入与历史股价共同作为预测模型输入。不同于以往仅针对单只股票的研究，本方法训练一个可应用于多只股票的通用模型。实验表明，相比基线模型，平均绝对误差（MAE）降低了7.11%，验证了股票名称嵌入在新闻过滤与跨股票预测中的有效性。
原文摘要 · Abstract (English)
Predicting stock prices presents challenges in financial forecasting. While traditional approaches such as ARIMA and RNNs are prevalent, recent developments in Large Language Models (LLMs) offer alternative methodologies. This paper introduces an approach that integrates LLMs with daily financial news for stock price prediction. To address the challenge of processing news data and identifying relevant content, we utilize stock name embeddings within attention mechanisms. Specifically, we encode news articles using a pre-trained LLM and implement three attention-based pooling techniques -- self-attentive, cross-attentive, and position-aware self-attentive pooling -- to filter news based on stock relevance. The filtered news embeddings, combined with historical stock prices, serve as inputs to the prediction model. Unlike prior studies that focus on individual stocks, our method trains a single generalized model applicable across multiple stocks. Experimental results demonstrate a 7.11% reduction in Mean Absolute Error (MAE) compared to the baseline, indicating the utility of stock name embeddings for news filtering and price forecasting within a generalized framework.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。