Predictability of Post-Earnings Announcement Drift with Textual and Contextual Factors of Earnings Calls
Study on predicting Post-Earnings Announcement Drift using textual and contextual features from earnings calls.
What it examines
This paper examines the effectiveness of incorporating textual and contextual features from earnings calls to predict Post-Earnings Announcement Drift (PEAD) using computational linguistics and large language models, focusing on S&P500 constituents from 2010 to 2022.
What it concludes
The research highlights the importance of contextual features in improving PEAD prediction models. Potential applications include enhancing trading strategies and financial analysis. Future research could explore further refinement of textual features and their integration with contextual data.
Evidence objects
The research highlights the importance of contextual features in improving PEAD prediction models. Potential applications include enhancing trading strategies and financial analysis. Future research could explore further refinement of textual features and their integration with contextual data.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Predictability of Post-Earnings Announcement Drift with Textual and Contextual Factors of Earnings Calls Andy Chung Department of Advanced Interdisciplinary Studies, Graduate School of Engineering, The University of Tokyo Tokyo, Japan andy@g.ecc.u-tokyo.ac.jpKumiko Tanaka-Ishii Department of Computer Science and Engineering, School of Fundamental Science and Engineering, Waseda University Tokyo, Japan kumiko@waseda.jp ABSTRACT Post-Earnings Announcement Drift (PEAD), a well-known anomaly in financial markets, describes the tendency of cumulative stock returns to drift in the direction of an earnings surprise for a pro- longed period following an earnings announcement. Numerous studies have used a supervised learning approach to predict PEAD, using earnings, fundamental and technical factors. However, there is a lack of study on how the context of the earnings call can be used for the PEAD prediction task. This paper uses computational linguistics techniques and large language models to
Source row: 1564 · abstract type: unknown