TREE-BASED MACHINE LEARNING MODELS TO PREDICT INTERNATIONAL TOURIST ARRIVALS IN INDONESIA DURING COVID-19 PANDEMIC

• Main Author: Agus Afrianto, Mochammad
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/56693
• Institution: Institut Teknologi Bandung

This thesis focuses on developing two tree-based machine learning models – the extreme gradient boosting (XGBoost) and the random forest models – to predict international tourist arrivals in Indonesia during the Corona Virus Disease 2019 (COVID-19) pandemic. The performance of these models is compared to that of well-investigated prediction models such as the artificial neural network (ANN), autoregressive integrated moving average (ARIMA), and seasonal ARIMA (SARIMA), in the context of tourist arrival predictions. The researchers analyzed 18 years (January 2002–October 2020) of monthly tourist arrival data collected by the Central Bureau of Statistics Indonesia. The analysis also included news reports on new COVID-19 cases and related government interventions as data inputs. The study's findings indicate that XGBoost has superior prediction accuracy compared to other models in terms of the mean absolute percentage error (MAPE), coefficient of variation (CV), and root mean square error (RMSE).