Stock Prediction

In the wake of the GameStop and AMC frenzies, financial firms and researchers have been racing to decode one question: Can social media sentiment predict stock prices? A new paper from researchers at Wrocław University of Science and Technology provides a sobering answer: not really. Despite employing advanced sentiment models—including a ChatGPT-annotated and emoji-savvy version of Financial-RoBERTa—the study found only weak and inconsistent relationships between sentiment and price movement for GME and AMC. ...

Can a model trained to think like a day trader ever truly understand long-term market moves? Most financial AI systems today seem stuck in the equivalent of high-frequency tunnel vision — obsessed with predicting tomorrow’s returns and blind to the richer patterns that shape actual investment outcomes. A new paper, NGAT: A Node-level Graph Attention Network for Long-term Stock Prediction, proposes a more grounded solution. It redefines the task itself, the architecture behind the prediction, and how we should even build the graphs powering these systems. ...