Deep learning in the Chinese stock market: The role of technical indicators

Abstract

A convolutional neural network (CNN) is applied to forecast stock price changes in the Chinese stock market. We use 27 technical indicators and 5 original price series as benchmark model setting and further explore the model forecasting performance with social media sentiment. Our results show that our model could obtain 70% forecasting accuracy on average. Moreover, social media sentiment could increase the forecasting performance for both indexes and individual stocks.