Deep Learning Approach for Short-Term Stock Trends Prediction Based on Two-Stream Gated Recurrent Unit Network

Abstract

Financial news has been proven to be a crucial factor which causes fluctuations in stock prices. However, previous studies heavily relied on analyzing shallow features and ignored the structural relation among words in a sentence. Several sentiment analysis studies have tried to point out the relationship between investors' reaction and news events. However, the sentiment dataset was usually constructed from the lingual dataset which is unrelated to the financial sector and led to poor performance. This paper proposes a novel framework to predict the directions of stock prices by using both financial news and sentiment dictionary. The original contributions of this paper include the proposal of a novel two-stream gated recurrent unit network and Stock2Vec-a sentiment word embedding trained on financial news dataset and Harvard IV-4. Two main experiments are conducted: the first experiment predicts S&P 500 index stock price directions using the historical S&P 500 prices and the articles crawled from Reuters and Bloomberg, and the second experiment forecasts the price trends of VN-index using VietStock news and stock prices from cophieu68. Results show that: 1) two-stream GRU outperforms state-of-the-art models; 2) Stock2Vec is more efficient in dealing with financial datasets; and 3) applying the model, a simulation scenario proves that our model is effective for the stock sector.