A Comparative Study on SSE 50 Index Prediction Based on ARIMA Model and LSTM Neural Network

SSE 50 Index is the stock index of Shanghai Stock Exchange, representing the top 50 companies by “float-adjusted” capitalization and other criteria, which is a key indicator of the China stock markets and has an important influence on investment decisions. Therefore, how to predict stock price trend has become a significant problem in the field of financial data analysis. The purpose of this paper is to predict the stock market trend and compare the models with the prediction of SSE 50 Index. In this paper, Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) are established to predict the closing price with the historical transaction data of SSE 50 Index. The research results show that LSTM neural network is better than ARIMA model in prediction accuracy and prediction stability, which is of importance in the market prediction.