Extracting the Structure of Press Releases for Predicting Earnings Announcement Returns

By Yuntao Wu, Ege Mert Akin, Charles Martineau, Vincent Grégoire, Andreas Veneris

Published 2025-10-04

Everscope rating

1923.5

Relevance to quantitative trading

8 / 10

Implementation complexity

7 / 10

Reproducibility

3 / 5

About this paper

Methodology: Multi-model NLP-based return prediction with rolling window online learning. Problem types: Regression, Natural Language Processing, Online Learning, Ranking, Dimensionality Reduction, Topic Modeling.

arXiv:2509.24254 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.