TCL: Trend-consistent Contrastive Learning for Stock Movement Prediction

Global stock dynamics deeply influence stock price movements, which are often reflected in the consistent trends of the market index and individual stock prices. Nevertheless, external events (e.g., economic policies and geopolitics) and stock industry features could make special cases where local stock price movements deviate from market index trends. In these cases, investors and financial analysts can often identify and make reasonable investment decisions based on their investment experience and knowledge of the global market index trend and specific stocks. We argue that these investment insights can be incorporated into the model to make a more accurate decision. However, few existing works investigate this issue. In this paper, we design a novel prompt to introduce investment experience knowledge and introduce a trend-consistent contrastive learning strategy into the model to improve awareness of the relationship between the stock and the market. Specifically, by pulling stocks with consistent trends closer together and moving stocks with inconsistent trends apart, the model is expected to learn more personalized relationships between individual stocks and the global market. In this way, our model is able to provide more accurate and comprehensive stock analysis and prediction. We conduct extensive experiments on the public dataset, and the results demonstrate the effectiveness of our model.