This paper estimates the economic losses in Indonesia's tourism sector due to the COVID-19 pandemic using an Autoregressive Integrated Moving Average Model (SARIMA). Additionally, an autoregressive distributed lag model (ARDL) is employed to estimate the demand for tourism in Indonesia from the six largest inbound tourist countries, from 1989 to 2019. The results predict a decrease of nearly 16.65 million tourists and a potential loss of US$19.07 billion from January 2020-March 2021. Income per capita, relative prices, and substitution prices significantly impact the demand from overseas travelers for tourism opportunities in Indonesia. Tourism in Indonesia is considered as a luxury with a competitive price. The country could capitalize on the high willingness to pay of foreign tourists, strong income elasticity, and a positive perception of Chinese tourists. Complementary tourism promotion policies from neighboring countries could help to attract more Chinese visitors. Inbound tourism from India may experience the largest negative impact from COVID-19 due to the large income elasticity, negative price elasticity, and a possible substitution in destinations amid changes in prices. Tourists from Singapore and Australia may soon revisit as they see Indonesia as an inexpensive destination. Japan may revisit depending on whether tourism prices in Indonesia remain competitive or not. Policy makers may investigate non-price policies as price-oriented ones will not be very effective.

This study uses an autoregressive distributed lag (ARDL) model to investigate the role of incomes, relative price competitiveness, and substitution prices in tourism demand from Indonesia’s six largest countries of origin from 2007Q1 to 2019Q4. Income level, competitive prices, and substitution prices significantly impact the demand for tourism in Indonesia. Malaysia, Singapore, Australia, Japan, and India are income elastic, signaling that tourism is a luxury good, but China (normal good). Malaysia and China are price elastic while Japan, India, Singapore, and Australia are less affected by changes in relative prices. Substitute prices may drive tourist to other destinations if the change in prices is large.

The demand for tourism in Indonesia continues to increase every year but cannot reach thepredetermined target. Studies on tourism demand have been done a lot, especially in Indonesia.The selection of the dependent variable in tourism demand is not problematic and acceptable,however, the selection of the independent variable is still unclear. This study aims to provide anappropriate Indonesian tourism demand model and analyze the determinants of tourism demandin Indonesia. The estimation technique used is a static panel regression. The results of this studyprove that there is multicollinearity in the tourism demand model when exchange rate and relativeprice are combined into one model, showing that relative price are good proxies in representingtourism price, and showing that substitution price are the main determinants of tourism demand inIndonesia. The policy implications recommended in this study are monitoring the economicgrowth of the origin countries of most tourists visiting Indonesia, improving the qual ity ofIndonesian tourism, and developing the Wonderful Indonesia program.