Flight Delay Prediction Based on Gradient Boosting Ensemble Models

EasyChair Preprint 8511, version 1

Abstract

In recent years, the volume of airline transportation has increased with the rapid development of civil aviation. With the increasing demand for flights, aviation faces the flight delay problem, and it becomes a series of issues that needs to be addressed efficiently. Correct prediction of flight delays can improve airport operations efficiency and passenger travel comfort. In the present research, a machine learning flight delay prediction model is established with the help of Gradient boosting ensemble models. Three different gradient boosting techniques such as CatBoost, LightGBM, and XGBoost applied to the Airline dataset. To validate the performance and efficiency of the proposed method, a comparative analysis is performed. The comparative results show that the CatBoost improves the prediction accuracy by maintaining stability.

Keyphrases: CatBoost, GBoost, LightGBM, XGBoost, airline, delay prediction, machine learning

@booklet{EasyChair:8511,
  author    = {Rahemeen Khan and Tooba Zahid},
  title     = {Flight Delay Prediction Based on Gradient Boosting Ensemble Models},
  howpublished = {EasyChair Preprint 8511},
  year      = {EasyChair, 2022}}