Abstract

The future trend prediction of time series represented by stock price has always been a key research topic in the field of data science. The rapid development of deep learning makes the analysis and prediction of time series enter a new stage. Deep learning algorithm represented by deep neural network can effectively overcome the shortcomings of traditional time series analysis methods. This paper first introduces the principle and structure of the recurrent neural network (RNN) model in the deep neural network. In view of the problem that the gradient vanishes easily and cannot effectively analyze the long sequence data, this paper introduces the gating structure to improve the hidden layer of the RNN, so as to construct the long short-term memory (LSTM) neural network model. In this paper, the LSTM neural network model is applied to the stock price prediction, and the prediction results are compared with the RNN model. The experimental results show that the error value of the LSTM neural network model is smaller than that of the RNN model, and has better prediction effect. Therefore, the LSTM neural network model is more suitable for the prediction of stock price.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call