<![CDATA[Indonesia has diversity and natural wealth that attracts tourism in Indonesia. Tourism is one of the industries that provides the highest foreign exchange for the country because it has a positive impact. However, the existence of COVID-19 has resulted in a decrease in the number of visits due to restrictions on foreign tourists. From January to November 2021, there was a drastic decrease of 61.82% in the number of foreign tourist visits compared to the same period in 2020. In addition to COVID-19, as well as support in building facilities that support the increase in the number of foreign tourists. From these conditions, predictions are needed that are used as a basis for planning and helping decision making. The purpose of this study is to develop a more accurate prediction model in similar studies using the same data in predicting foreign tourist arrivals in Indonesia through air entrances using the XGBoost, Random Forest, and Catboost methods by focusing on the accuracy evaluation results metrics RMSE, MAE, and MAPE and making predictions for the next 12 months. The dataset used is taken from the Central Statistics Agency (BPS), namely data on foreign tourist arrivals based on the arrival entrance in the period January 2017 to November 2021. The data used are time series and non-stationary. From the research results, it can be seen based on the accuracy evaluation results that the XGBoost model of this study gets better accuracy evaluation results than the other two models by getting the results of the RMSE accuracy evaluation value of 671935.2, MAE 648139.1, and MAPE 20985.35. The XGBoost model is better with a smaller accuracy error value than the Random Forest model, Catboost, and similar research using the ARIMA method with an RMSE value of 779670.7, MAE 749030.4, and MAPE 23196.45.]]>
Copyrights © 2024
