Share Price Trend Prediction Using CRNN with LSTM Structure

Abstract

The stock market plays an important role in the entire financial market, and the prediction of stock price volatility is one of the most attractive research issues. In this paper, we will use the historical information of stocks to predict future stock prices and use deep learning to achieve them. This paper uses deep learning to predict the future trend of stock prices. Since the trend of stocks is usually related to the previous stock price, this paper proposes a Convolutional Recurrent Neural Network (CRNN)-based architecture, ConvLSTM, in which long and short-term memory is used in RNN (Long short). -term memory, LSTM) architecture. LSTM improves the long-term dependence of traditional RNN and effectively improves the accuracy and stability of prediction. This paper collects a total of ten stock historical data to test and achieve an average error rate of 3.449 RMSE.