Exploring Multi-Time Context Vector and Randomness for Stock Movement Prediction

We propose a novel stock movement prediction model that learns Multi-Time Contexts and Randomness (MTC-R). We assume that the stock price movements are affected by (1) combination of time-based momentums and (2) tradings by noise traders which cause randomness in a stock market. MTC-R has three main procedures for modeling our hypothesis. First, the model learns time representations using time2vec and encodes the multi-time views using a GRU network. Second, MTC-R generates the multi-time contexts using a multi-head attention mechanism and inserts the randomness. Third, a loss function is designed to learn temporal differences between the results of the second and the current time-embedded vector. Our model improves the prediction results in terms of accuracy and the Matthews correlation coefficient on six benchmark datasets compared to baseline models. Furthermore, MCT-R shows the effectiveness of the prediction results using cumulative returns in portfolio trading simulations.