Predicting Stock Price Direction on Earnings Announcement Days using Multi-modal Deep Learning
For quantitative traders and investors, this work offers a method to improve prediction of earnings-day stock movements, though the gains are incremental over existing approaches.
This study predicts stock price direction on earnings announcement days using a multi-modal model combining fundamentals, technical indicators, and news sentiment. The Transformer model achieved a higher macro F1-score than LSTM and logistic regression, with sentiment features providing consistent improvement.
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 predict the directional price movement of equities on EA days. We construct a multi-modal feature space combining 15 fundamental metrics, 3 price-based technical indicators and sentiment scores derived from financial news articles processed using FinBERT. We compare a Long Short-Term Memory (LSTM) network and a Transformer-based architecture against a logistic regression baseline, and further assess all models with and without sentiment features to quantify their incremental value. Our results indicate that while the LSTM demonstrates higher precision through a conservative safe-bet strategy, the Transformer model exhibits superior sensitivity in identifying volatile movements, achieving a higher macro F1-score, with ablation experiments showing a consistent benefit from incorporating news sentiment.