Researchers have developed a multi-modal deep learning approach to predict stock price direction on earnings announcement days. The study combines fundamental metrics, technical indicators, and sentiment analysis from financial news processed by FinBERT. Both LSTM and Transformer architectures were evaluated, with the Transformer showing superior sensitivity to volatile movements and a higher F1-score, demonstrating a consistent benefit from incorporating news sentiment. AI
IMPACT This research demonstrates the potential of multi-modal deep learning, specifically incorporating news sentiment, to improve financial market predictions.
RANK_REASON The cluster contains an academic paper detailing a new research methodology and model evaluation.
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
