StonkBERT: Can Language Models Predict Medium-Run Stock Price Movements?

Abstract: To answer this question, we fine-tune transformer-based LLMs, including BERT, on different sources of company-related text data for a classification task to predict the one-year stock price performance. We use three different types of text data: News articles, blogs, and annual reports. This allows us to analyze to what extent the performance of LLMs is dependent on the type of the underlying document. StonkBERT, our transformer-based stock performance classifier, shows substantial improvement in predictive accuracy compared to traditional LLMs. The highest performance was achieved with news articles as text source. Performance simulations indicate that these improvements in classification accuracy also translate into above-average stock market returns.