Forecasting the Number of Ship Passengers with SARIMA Approach (A Case Study: Semayang Port, Balikpapan City)

Abstract

From year to year, the number of ship passengers at Semayang Port, Balikpapan city tends to fluctuate. It also doubles in certain months and repeats every year. Sea transportation companies need to make forecasts in order to implement policies related to predict the number and capacity of ships that need to be provided as well as the preparation of port facilities. The study aims at obtaining the best model, predicting and determining the accuracy of the forecasting results for the number of passengers arriving and departing at Semayang Port, Balikpapan city using SARIMA method. The SARIMA method is a time series data forecasting method that is able to identify seasonal patterns. The results showed that the best model for predicting the number of passengers departing at Semayang Port, Balikpapan city is the SARIMA (4,1,0)(0,1,2)12 model with a MAPE of 14.05%. It means that the SARIMA model used produces good forecasting. Meanwhile, the best model to predict the number of passengers coming to Semayang Port Balikpapan city is the SARIMA (0,1,1)(2,1,0)12 model with a MAPE value of 3.27% which exposes that the SARIMA model used succeed to provide accurate forecasting. The results of this forecast can be used as a reference for the government or port managers to anticipate a surge in passengers. The government or port management can prepare an adequate amount of transportation in certain months to avoid the accumulation of passengers and to make sea transportation more efficient.