Extracting the Structure of Press Releases for Predicting Earnings Announcement Returns
Authors:
- Yuntao WuYWYuntao Wu
- Ege Mert AkinEAEge Mert Akin
- Charles MartineauCMCharles Martineau
- Vincent GrégoireVGVincent Grégoire
- Andreas VenerisAVAndreas Veneris
Preprint
Abstract
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.Keywords
All Related Versions
- Version 1, 2025-09-29, ArXiv
- Version 2, 2025-10-04, ArXiv
- Published version: , 596.
This publication has 15 references indexed in Scilit:
- ECC Analyzer: Extracting Trading Signal from Earnings Conference Calls using Large Language Model for Stock Volatility Prediction2024
- Business News and Business CyclesThe Journal of Finance, 2024
- The colour of finance wordsJournal of Financial Economics, 2023
- PEAD.txt: Post-Earnings-Announcement Drift Using TextJournal of Financial and Quantitative Analysis, 2022
- Price revelation from insider trading: Evidence from hacked earnings newsJournal of Financial Economics, 2022
- Rest in Peace Post-Earnings Announcement DriftCritical Finance Review, 2022
- How is Earnings News Transmitted to Stock Prices?Journal of Accounting Research, 2021
- Earnings conference calls and stock returns: The incremental informativeness of textual toneJournal of Banking & Finance, 2012
- The Extreme Future Stock Returns Following I/B/E/S Earnings SurprisesJournal of Accounting Research, 2006
- Analysis of regression in game theory approachApplied Stochastic Models in Business and Industry, 2001