FARISI, MUHAMAD NABIEL YUDHI (2025) ANALISIS DAN PREDIKSI HARGA TIKET PESAWAT BERDASARKAN TREN PASAR MENGGUNAKAN XGBOOST. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (222kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
Bab 1.pdf Restricted to Registered users only Download (108kB) |
|
|
Text (BAB II)
Bab 2.pdf Restricted to Registered users only Download (215kB) |
|
|
Text (BAB III)
Bab 3.pdf Restricted to Registered users only Download (112kB) |
|
|
Text (BAB IV)
Bab 4.pdf Restricted to Registered users only Download (428kB) |
|
|
Text (BAB V)
Bab 5.pdf Restricted to Registered users only Download (81kB) |
|
|
Text (DAFTAR PUSTAKA)
Daftar Pustaka.pdf Restricted to Registered users only Download (93kB) |
|
|
Text (LAMPIRAN)
Lampiran.pdf Restricted to Registered users only Download (963kB) |
Abstract
The airline industry experiences volatile ticket pricing influenced by factors such as seasonality, market demand, government regulations, and fuel prices. This research aims to analyze market trends in airline ticket pricing and develop a price prediction model using the Extreme Gradient Boosting (XGBoost) algorithm. The dataset used consists of historical airline ticket prices for both domestic and international routes from 2019 to 2024. The research process includes data preprocessing, feature engineering, variable selection, model training, and performance evaluation using RMSE, MAE, MAPE, and R² metrics. The results show that XGBoost delivers higher prediction accuracy compared to linear regression and Random Forest methods. The proposed model is able to predict ticket prices more accurately and helps consumers identify the best time to purchase tickets. Additionally, the model can serve as a strategic reference for airlines and regulators in developing more efficient pricing policies based on market trends. Keywords : XGBoost, ticket price prediction, machine learning, market trend, ensemble algorithm. Industri penerbangan mengalami dinamika harga tiket yang fluktuatif, dipengaruhi oleh berbagai faktor seperti musim, permintaan pasar, kebijakan pemerintah, dan harga bahan bakar. Penelitian ini bertujuan untuk menganalisis tren pasar harga tiket pesawat serta membangun model prediksi harga menggunakan algoritma Extreme Gradient Boosting (XGBoost). Data yang digunakan berupa data historis harga tiket pesawat domestik dan internasional dari tahun 2019 hingga 2024. Proses penelitian meliputi preprocessing data, feature engineering, pemilihan variabel penting, pelatihan model prediksi, serta evaluasi performa menggunakan metrik RMSE, MAE, MAPE, dan R². Hasil penelitian menunjukkan bahwa XGBoost memberikan tingkat akurasi yang tinggi dibandingkan metode regresi linier dan Random Forest. Model yang dibangun mampu memberikan prediksi harga tiket secara lebih akurat dan membantu konsumen dalam menentukan waktu terbaik untuk membeli tiket. Selain itu, model ini juga dapat menjadi referensi strategis bagi maskapai dan regulator dalam menyusun kebijakan harga berbasis tren pasar secara lebih efisien. Kata kunci: XGBoost, prediksi harga tiket, machine learning, tren pasar, algoritma ensemble.
Actions (login required)
 |
View Item |
