Stock Market’s Price Movement Prediction with Multi-branch LSTM and Technical Analysis

The relationship between technical indicators and stock market trading decision-making is investigated in this paper. Inspired by the technical analysis method, the technical indicators that are used as auxiliary information in many studies are the only source of information given to the prediction model proposed in this paper. The integrated learning method is used to combine the technical indicators and prediction models into a multi-branch Long Short-Term Memory (LSTM) network. Prediction accuracy is obtained when various technical indicators are used as the input of the prediction model. The experiment results show that a combination of neural networks and technical indicators can achieve better prediction accuracy in the task of stock price movements. This multi-branch LSTM model has achieved an accuracy of 70% when predicting the stock price movement of the Shanghai Composite Index.