PREDIKSI KETERLAMBATAN KEDATANGAN PENERBANGAN DENGAN METODE MACHINE LEARNING

Flight Delay is a problem in Indonesia's growing aviation industry. The delay causes unscheduled traffic congestion and lowers the level of service in the air traffic controller. This study aims to create a flight prediction model using machine learning. The method in this study is a compari...

全面介紹

Saved in:
書目詳細資料
主要作者: Rizki Oktafianto, Muhammad
格式: Final Project
語言:Indonesia
在線閱讀:https://digilib.itb.ac.id/gdl/view/50685
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
實物特徵
總結:Flight Delay is a problem in Indonesia's growing aviation industry. The delay causes unscheduled traffic congestion and lowers the level of service in the air traffic controller. This study aims to create a flight prediction model using machine learning. The method in this study is a comparison of the implementation of 11 machine learning algorithms on flight data to Bandung to obtain prediction results for delays and model analysis using Local Interpretable Model-Agnostic Explanations (LIME). The best results from modeling with machine learning show the achievement level of the accuracy value of 91,5% and the AUC value on the ROC graph of 0,966 on the bagging classifier model with decision trees basis. Analysis of feature importance shows that the most significant factor is traffic at origin airport. The results of this study can be used to create a flight delay prediction system.