Prior prediction of flight arrival delays is necessary for both travelers and airlines because delays in flights not only trigger huge economic loss but also airlines end up losing their reputation that was built for several years and passengers lose their valuable time. Our paper aims at predicting the arrival delay of a scheduledindividual flight at the destination airport by utilizing available data. The predictive model presented in this work is to foresee airline arrival delays by employing supervised machine learning algorithms. US domestic flight data along with the weather data from July 2019 to December 2019 were acquired and are used while training the predictive model. XGBoost and linear regression algorithms were applied to develop the predictive model that aims at predicting flight delays. The performance of each algorithm was analyzed. Flight data along with the weather data was given to the model. Using this data, binary classification was carried out by the XGBoost trained model to predict whether there would be any arrival delay or not, and then linear regression model predicts the delay time of the flight.
Machine Learning Model - based Prediction of Flight Delay
07.10.2020
1195552 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Flight Delay Prediction using Machine Learning Model
IEEE | 2022
|Flight delay prediction based on machine learning method
SPIE | 2024
|Flight Arrival Delay Prediction Using Supervised Machine Learning Algorithms
Springer Verlag | 2021
|Departure Flight Delay Prediction and Visual Analysis Based on Machine Learning
SAE Technical Papers | 2023
|