PREDICTION NUMBER OF TOURIST ARRIVALS & PASSENGERS AT THE AIRPORT USE THE TIME MODEL FORCESTING SERIES

Abstract

The progress of tourism in today's life is very common in every country in the world. Improving the quality of tourism is very important for every country, considering that tourism is one of the sources of state income. Therefore, one of the most important parameters for this is knowing the number of visitors or tourists at any time, and being able to utilize existing historical data to predict the number of tourists in the future. In this research, prediction/forecasting of the number of tourists and passengers at the airport will be carried out using the Seasonal Auto Regressive Integrated Moving Average (SARIMA), Long-short Term Memory (LSTM), and Prophet methods on two time series datasets with monthly frequency. Of the three forecasting models, the results of each were obtained and then compared, the SARIMA model was the model with the best performance with the smallest RMSE and MSE values.