Author(s)

Shichen Qiu, Fan Pei, Feiyue Shang

Corresponding Author

Shichen Qiu

ABSTRACT

In this paper, we use the deep learning method to predict the rising and falling direction of the Shanghai and Shenzhen 300 index from 2012 to 2019. After feature extraction is carried out by using convolution neural network and short-term memory model on multiple time scales, the final prediction results are obtained by splicing the feature matrices on different time scales. Compared with other models, the experimental results show that the multi-time-scale CNN-LSTM model proposed in this paper can effectively improve the effect of forecasting the rise and fall of CSI 300 index and make a profit in the trading back test. The research content of this paper enriches the methods of financial time series data analysis, which can not only provide decision-making reference for investors, but also help to enhance the understanding of the laws of the financial market.

KEYWORDS

Deep learning, neural network, stock price, LSTM, CNN