An Alternative Forecasting Using Holt-Winter Damped Trend for Soekarno-Hatta Airport Passenger Volume
Located in the capital city of Indonesia, Soekarno-Hatta Airport is considered as the main airport. Since there are some aviation companies providing low cost flight, the number people coming and leaving trough this airport has increased. The passenger volume can be considered as seasonal data since it shows increment in particular months, such as long holiday. Knowing in advance the volume of passenger will help the government to improve its service effectively. There is a simple and accurate method for forecasting seasonal data that is called Holt-Winter Exponential Smoothing (HWE). However, HWE always encounters over forecasting problem when it is employed to forecast in some future periods (m>1). In order to solve this problem, we add the damped parameter that will be damping the exponentially growth on HWE. This method called HWE damped trend. We employed the domestic passenger volume data of Soekarno-Hatta Airport from January 2008 till December 2015. This data collected from prior research. As the result, HWE damped trend outperforms traditional HWE on either training data set or testing data.
holt-winter, holt-winter damped trend, trust-region-reflective algorithm
Faculty of Mathematics and Natural Science
Universitas Islam Indonesia, Yogyakarta
Jurnal EKSAKTA is licensed under a Creative Commons Attribution ShareAlike 4.0