Forecasting The Number of ASEAN Tourists in Indonesia: The Impact of The COVID-19 Pandemic Using Intervention Analysis

The COVID-19 pandemic has had a significant impact on Indonesia’s tourism sector, particularly on the number of tourist arrivals from ASEAN countries. International travel restrictions led to a drastic decline in visitor numbers. This study aims to forecast the number of ASEAN tourists visiting Indonesia using an intervention analysis based on the Autoregressive Integrated Moving Average (ARIMA) model to capture both the pandemic shock and the subsequent recovery phase. The data used are secondary data from Statistics Indonesia (BPS) covering the period January 2017–November 2024, with the training data divided into three phases: the pre-pandemic period (January 2017–January 2020), Intervention I or the pandemic period (February 2020–April 2022), and Intervention II or the recovery period (May 2022–December 2023). Testing data are used to evaluate forecasting performance for the period January 2024–November 2024. The results show that the ARIMA(2,1,0) model with a step-type intervention successfully captures significant changes in the data pattern, yielding a Mean Absolute Percentage Error (MAPE) of 14.91% on the training data—an improvement over both the non-intervention model (MAPE 86.31%) and the first intervention model (MAPE 56.68%). On the testing data, the model achieves even higher accuracy with a MAPE of 8.21%, indicating that the intervention model effectively represents the dynamics of the pandemic impact and the subsequent recovery.