Predicting Stock Price Direction on Earnings Announcement Days using Multi-modal Deep Learning
arXiv:2605.25894v1 Announce Type: new Abstract: 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 S
The accelerating pace of AI development, particularly in large language models and multi-modal architectures, enables more sophisticated analysis of unstructured financial data like news sentiment, making previously unfeasible predictions possible.
This research demonstrates a tangible application of advanced AI in financial markets, potentially offering new tools for institutional investors and impacting market efficiency through improved predictive capabilities.
The ability to integrate diverse data types (fundamentals, technicals, news sentiment) through multi-modal deep learning changes how analysts might approach short-term stock price forecasting, specifically around earnings events.
- · Quantitative hedge funds
- · AI/ML powered financial analytics platforms
- · High-frequency trading firms
- · Financial data providers
- · Traditional fundamental research analysts
- · Retail investors relying on basic research
Increased adoption of multi-modal AI models for financial forecasting and trading strategies.
Financial markets may become more efficient as AI-driven models rapidly price in diverse information, potentially reducing alpha opportunities over time.
Regulatory scrutiny around the use of complex AI in financial markets could increase due to potential for market manipulation or systemic risks.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG