DATA ANALYTIC FOR FORECASTING ARRIVAL OF FOREIGN TOURISM IN INDONESIA

• Main Author: Haqiq, Asyeh
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/43171
• Institution: Institut Teknologi Bandung

Tourism has been planned to become a major income in various countries, including Indonesia. To support government programs, accurate data is needed related to forecasting tourist visits and what factors influence foreign tourist visits. Previous research has shown that online search data can be used to estimate tourist visits. Massive query data becomes its challenge in determining the right kata kuncis to use to build indexes. This study proposes a framework for building a composite search index. In contrast to previous studies that predict the number of tourist visits to a tourist attraction, city or city-state. This study predicts foreign tourist arrivals at the country level. The data used in this study are the Google Trends Index, CPI, average exchange rate, average exchange rate, and the number of disaster events. By using the VECM econometric model, this study aims to find what variabels are influencing and how the influence of each variabel on foreign tourist visits. Forecasting uses the Vector Error Correction Model (VECM) method then analyzes the model, provides forecasting and structural analysis of the model. The results of the model analysis are long-term and short-term analyzes. Furthermore, this study compares the VECM econometric forecasting method with SVR machine learning by looking at the MAPE results of each method. The analysis shows that the variabel of foreign tourist visits itself becomes the dominant factor in determining the next tourist visit. The Google Trends index effects in the middle period.