文本内容比财报数据更能预测公司收益公告日股价波动
Extracting the Structure of Press Releases for Predicting Earnings Announcement Returns
- 用FinBERT分析新闻稿文本，捕捉软信息价值
- 软信息预测力与盈利意外相当，结合模型提升效果
- 适合金融量化、市场微观结构研究者参考
我们研究了2005至2023年间超过13.8万份收益新闻稿中的文本特征对收益公告日股票回报的预测能力。对比传统词袋模型与BERT-based嵌入方法，发现新闻稿内容（软信息）的预测力与盈利意外（硬信息）相当，其中FinBERT表现最优。融合多种模型可增强解释力与预测强度。股价在开盘时已充分反映新闻稿内容；若新闻稿提前泄露，则具备预测优势。主题分析揭示管理层叙事存在自我美化偏差。该框架通过在线学习实现实时回报预测，兼具可解释性，并揭示语言在价格形成中的细微作用。
原文摘要 · Abstract (English)
We examine how textual features in earnings press releases predict stock returns on earnings announcement days. Using over 138,000 press releases from 2005 to 2023, we compare traditional bag-of-words and BERT-based embeddings. We find that press release content (soft information) is as informative as earnings surprise (hard information), with FinBERT yielding the highest predictive power. Combining models enhances explanatory strength and interpretability of the content of press releases. Stock prices fully reflect the content of press releases at market open. If press releases are leaked, it offers predictive advantage. Topic analysis reveals self-serving bias in managerial narratives. Our framework supports real-time return prediction through the integration of online learning, provides interpretability and reveals the nuanced role of language in price formation.
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。