The price fluctuations in the stock market are regarded as a barometer of economic development.Accurate prediction of stock prices has always been the focus of many researchers.With the continuous application and development of artificial intelligence technology and big data technology,as well as the huge fluctuations in stock prices caused by domestic economic changes and inter-national situation changes during the epidemic,it has become increasingly important to accurately predict stock prices.This article predicts the stock price of Shanghai Pudong Development Bank(600000)based on the characteristics of the stock market and the properties of LSTM(Long Short Term Memory)recurrent neural network.The experimental results show that the LSTM model has small errors and high accuracy in predicting stock prices,and has good prediction performance.