A Deep Fusion Model Combining News Content and Historical Prices for Stock Trend Prediction

Abstract

AbstractStock markets are often influenced by various factors which makes it very challenging to predict. Machine learning and deep learning models are often used to predict stock trends from its historical prices. Since there’s a lot of online information available in addition to stock prices, including technical indicators, news reports, and social information, we intend to combine news content for improving the performance. In this paper, we propose a deep fusion model for stock trend prediction combining news content with historical stock prices. Firstly, we utilize multi-layered Long Short-Term Memory (LSTM) to learn sequential information from stock prices. Then, we adopt Hybrid Attention Networks (HAN) which include both sentence-level and temporal attention to discover the relative importance of words from news reports. Finally, we compare early and late fusion models to improve stock trend prediction. The experimental results show that the best macro-F1 score of 79.0% can be achieved when we use late fusion to aggregate the prediction results of news content using 2-layer LSTM and that of historical prices in a 5-day window using HAN. As compared to individual models, the performance improvement of up to 40% can be obtained. This shows the potential of our proposed approach. Further investigation is needed for stock trend prediction in different markets.KeywordsStock trend predictionDeep learningSemantic analysis