MELKA PRATAMA, -
(2025)
THE FORECASTING FOR NUMBER OF AIRPLANE PASSENGERS AT INTERNATIONAL AIRPORT SOEKARNO HATTA, JAKARTA USING SOME TIME SERIES MODELS.
The Forecasting for Number of Airplane Passengers at International Airport Soekarno Hatta, Jakarta Using Some Time Series Models, 02 (01).
pp. 1-6.
ISSN 3050-5909
![[img]](http://repository.uin-suska.ac.id/86487/1.hassmallThumbnailVersion/JURNAL%20MELKA%20PRATAMA.pdf)  Preview |
|
Text (JURNAL MELKA PRATAMA)
JURNAL MELKA PRATAMA.pdf
- Published Version
Download (3MB)
| Preview
|
Abstract
ABSTRACT: Indonesia is a vast country comprising five major islands that serve as the economic centers. Consequently, transportation methods, such as airplanes, are essential for facilitating economic transactions between these islands. The number of airline passengers is a crucial component in fostering the growth of the air transportation industry, which significantly influences the economy between islands. Therefore, it is essential to conduct periodic analyses of passenger numbers. A forecast analysis that predicts the number of airline passengers for the upcoming period will offer valuable insights, enabling the air transportation
sector to continue its successful development. This research focuses on forecasting the monthly number of airplane passengers for the upcoming year at Soekarno-Hatta Airport, utilizing passenger data from January 2015 to August 2024. Four distinct time series models will be employed in this analysis: additive decomposition, multiplicative decomposition, Holt-Winters additive, and Holt-Winters multiplicative. The most critical aspect of evaluating the best model involves analyzing the smallest error results
from each model, utilizing the Mean Absolute Error (MAE) testing tool for this purpose. The Holt-Winters additive model emerges as the superior choice, while both the decompose additive and decompose multiplicative models were unable to generate data with sufficiently narrow gaps, particularly during the significant decline in passenger numbers caused by the COVID-19 pandemic.
KEY WORDS: forecasting, time series, decompose additive, decompose multiplicative, Holt Winters additive, Holt Winters multiplicative
Actions (login required)
 |
View Item |