Comparison of ARIMA Model and GM(1,1) Model in Passenger Flow Prediction of Sanya Airport

The airport is the infrastructure of air transportation, and its development planning, to a large extent, depends on the prediction of the busyness of future airport activities. The passenger flow of the airport is affected by many factors such as economic structure, population size, geographical location, industrial policy, comprehensive transportation, etc., so it conforms to the incomplete information characteristic of the gray system. ARIMA(1,1,1) and GM(1,1) models are applied to predict the passenger flow of Sanya Airport respectively, and the applicability of the two model is compared. The results show that the ARIMA(1,1) model is better than the GM(1,1) model in terms of single point maximum error, average relative error rate, average relative accuracy, and mean square error of relative error.