Research on Stock Prediction Model Based on Deep Learning

In order to obtain stable returns, this paper aims to establish a quantitative model with higher prediction accuracy. According to the time series characteristics of financial data, the prediction model with financial time series data is constructed by using the time-memory sequence model LSTM, which is applied to the representative SSE 50 series stocks. And based on this, the LSTM model with Encoder-Decoder mode and a hybridized framework of LSTM with CNN are built to improve the original model. Feature extraction is performed on the input data by using CNN, and then as an input to the LSTM, the extracted features are used for sequence prediction with the LSTM model.