Forecast Trafik Penerbangan di Indonesia Berdasarkan Data Google Trend dan Makroekonomi menggunakan Metode Long Short-Term Memory

Khafidli, Muhammad Khanif (2022) Forecast Trafik Penerbangan di Indonesia Berdasarkan Data Google Trend dan Makroekonomi menggunakan Metode Long Short-Term Memory. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6032202194-Master_Thesis.pdf Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Pandemi Covid-19 berdampak pada banyak sektor. Misalnya, di sektor penerbangan, trafik penerbangan turun drastis tanpa kepastian bisa pulih. Untuk itu diperlukan suatu metodologi untuk memprediksi trafik penerbangan guna memberikan perencanaan strategis pada operasional jadwal penerbangan, penataan rute, dan penentuan biaya layanan navigasi penerbangan. Namun, perkembangan saat ini terutama berfokus pada prakiraan lalu lintas penerbangan berdasarkan data historis tanpa mempertimbangkan faktor eksternal. Dalam penelitian ini, kami mengusulkan teknik Long Short-Term Memory (LSTM) untuk meramalkan trafik penerbangan di Indonesia yang melibatkan variabel eksternal seperti variabel makroekonomi dan google trends. LSTM diusulkan karena fleksibilitasnya untuk memodelkan data time series non-linier dan memiliki reputasi yang baik untuk akurasi prediksi. Kami pertama-tama memilih beberapa variabel di antara google trends dan makroekonomi menggunakan analisis nonlinier atau uji Terasvirta dan Cross Correlation Function (CCF). Kami kemudian menggunakan variabel yang dipilih untuk malakukan prediksi trafik penerbangan dan membandingkannya dengan variabel yang hanya menggunakan data trafik penerbangan historis. Dari Analisa yang telah kami lakukan dapat disimpulkan bahwa, dari 24 variabel prediktor yang digunakan terdapat 13 variabel yang mempunyai pola nonlinier dan berkorelasi secara signifikan, dengan adanya eliminasi variabel menggunakan uji Teravirta dan Cross Corelation Function mampu memperbaiki kinerja forecast trafik penerbangan menggunakan LSTM. Berdasarkan Root Mean Square Error (RMSE) dan Mean Absolute Percentage Error (MAPE), model yang melibatkan google trend mengungguli tiga model lainnya, yaitu model dengan hanya data historis, model dengan makroekonomi, dan model dengan makroekonomi dan google trends. Pasalnya, di era digital ini, google trends dapat mencerminkan psikologi populasi secara up-to-date.
==============================================================================================================================
The Covid-19 pandemic has impacted many sectors. For example, in the aviation sector, flight traffic went down drastically with no certainty of being recovered. This calls for a methodology to predict the flight traffic to provide strategic planning on flight schedules operational, route structuring, and flight navigation service cost determination. However, current developments mainly focus on flight traffic forecasting based on historical data without considering external factors. In this study, we propose the Long Short-Term Memory (LSTM) technique to forecast flight traffic in Indonesia involving external variables such as macroeconomic variables and google trends. LSTM is proposed because of its flexibility to model non-linear time series data and has a good reputation for predictive accuracy. We first select a few among google trends and macroeconomic variables using nonlinearity analysis and cross-correlation function (CCF). We then employ the selected variables to forecast the flight traffic and compare it to the one using only historical flight traffic data. Our results concluded, from the 24 predictor variables used, there are 13 variables that have nonlinear patterns and are significantly correlated at lag-1, with the elimination of variables using the Teravirta test and Cross Correlation Function able to improve the performance of flight traffic forecasts using LSTM. Based on the Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE), that the model involving google trend outperforms the other three models, i.e., the model with only historical data, the model with macroeconomics, and the model with both macroeconomic and google trends. It is because, in this digital era, google trends can reflect population psychology in an up-to-date manner..

Item Type:	Thesis (Masters)
Additional Information:	RTMT 658.403 55 Kha f-1 2022
Uncontrolled Keywords:	Cross Corelation Function, Mean Absolute Percentage Error, Root Mean Square Error, Time Series, dan Terasvirta.. Cross Corelation Function, Mean Absolute Percentage Error, Root Mean Square Error, Time Series, dan Terasvirta.
Subjects:	T Technology > T Technology (General)
Divisions:	Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User:	Mr. Marsudiyana -
Date Deposited:	09 Jul 2026 05:57
Last Modified:	09 Jul 2026 05:57
URI:	http://repository.its.ac.id/id/eprint/134580

Actions (login required)

View Item