THE APPLICATION OF SINGULAR SPECTRUM ANALYSIS METHOD IN FORECASTING THE NUMBER OF FOREIGN TOURISTS VISIT TO SPECIAL CAPITAL REGION OF JAKARTA

Abstract

Tourism has an important role for a society and a state as one of the supporting sectors for national development. Besides that, it is also an important factor for increasing people's income. Information regarding the estimated number of tourists in the past, present, and future is needed to establish a strategy or policy related to development in the tourism sector. Meanwhile, information about the required number of foreign tourists can be obtained using forecasting methods, one of which is the Singular Spectrum Analysis (SSA). This study aims to discuss the application of singular spectrum analysis (SSA) in predicting the number of foreign tourist visits to the Special Capital Region of Jakarta. There are two types of SSA forecasting methods, recurrent methods and vector methods. In its implementation, the performance of forecasting accuracy is influenced by the window length parameter. In this case, we are comparing several window length values, 10, 20, 30, and 40. In this study, a monthly number of foreign tourists visit to the Special Region of Jakarta from January 2011 to December 2019 was used. The results showed that the recurrent method with a window length of 40 resulted in a 16.6% smaller MAPE than the vector method. So, it can be concluded that the SSA method can predict the number of foreign tourists visiting the Special Capital Region of Jakarta well.