研究人员开发了一种多模态深度学习方法来预测财报发布日股票价格的方向。该研究结合了基本面指标、技术指标以及 FinBERT 处理的财经新闻中的情绪分析。对 LSTM 和 Transformer 架构都进行了评估，其中 Transformer 对波动性运动表现出更高的敏感性，F1 分数也更高，这表明纳入新闻情绪带来了持续的好处。 AI
影响 这项研究展示了多模态深度学习，特别是纳入新闻情绪，在改进金融市场预测方面的潜力。
排序理由 该集群包含一篇详细介绍新研究方法和模型评估的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.25894v1 Announce Type: new Abstract: Predicting stock price movements during Earnings Announcements (EAs) is a significant challenge due to market noise and high-impact price discontinuities. In this study, we evaluate whether pre-announcement news sentiment, firm fund…
Predicting stock price movements during Earnings Announcements (EAs) is a significant challenge due to market noise and high-impact price discontinuities. In this study, we evaluate whether pre-announcement news sentiment, firm fundamentals, and recent market dynamics jointly pre…
Predicting stock price movements during Earnings Announcements (EAs) is a significant challenge due to market noise and high-impact price discontinuities. In this study, we evaluate whether pre-announcement news sentiment, firm fundamentals, and recent market dynamics jointly pre…