ANNUAL PATTERN ANALYSIS AND FLIGHT FORECASTING AT INDONESIAN AIRPORTS USING SARIMA AND ARTIFICIAL NEURAL NETWORK METHODS

ROZIKIN, ICHSAN FACHRUL RYAN (2025) ANNUAL PATTERN ANALYSIS AND FLIGHT FORECASTING AT INDONESIAN AIRPORTS USING SARIMA AND ARTIFICIAL NEURAL NETWORK METHODS. Tugas Akhir thesis, Informatics.

Text 5210411284_ICHSAN FACHRUL RYAN ROZIKIN_ABSTRAK.pdf Download (11kB)

Abstract

Indonesia, as an archipelagic nation with the largest population in Southeast Asia, relies heavily on-air transportation to ensure accessibility across its vast regions. Air travel generates time series data due to its dependency on scheduled departures and consistent passenger flow. The continuous increase in air traffic each year necessitates strategic forecasting for optimizing resources and services. This study aims to forecast passenger, cargo, and baggage volumes at Indonesian airports using two models: Seasonal Autoregressive Integrated Moving Average (SARIMA) and Artificial Neural Network (ANN). The dataset, sourced from the Indonesian Central Statistics Agency (BPS), covers the period from 2016 to 2023. Evaluation metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) were used to assess prediction accuracy. Experimental results show that the best SARIMA model, SARIMA (0,0,0)(0,0,0), yielded MAE 0.34420, RMSE 0.34420, and MAPE 41.84% for passenger data; MAE 0.44631, RMSE 0.44631, and MAPE 56.78% for baggage; and MAE 0.63289, RMSE 0.63289, and MAPE 17.92% for cargo. In contrast, the ANN model with 20 epochs achieved better performance with MAE 0.25311, RMSE 0.25311, and MAPE 30.77% for passengers; MAE 0.02275, RMSE 0.02275, and MAPE 32.77% for baggage; and at 100 epochs, MAE 0.08828, RMSE 0.08828, and MAPE 2.50% for cargo. The ANN method demonstrated superior forecasting accuracy, making it a suitable approach for modelling annual air transportation trends in Indonesia due to its lower error rates. Keywords: Time Series, Airport, Forecasting, SARIMA, ANN, MAPE

Item Type:	Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User:	Kaprodi S1 Informatika UTY
Date Deposited:	17 Jul 2025 01:13
Last Modified:	17 Jul 2025 01:13
URI:	http://eprints.uty.ac.id/id/eprint/18186

Actions (login required)

View Item