A Comparative Study of Neural Networks and XGBoost Models for Flight Time Prediction

Authors

Ioannis Paraschos, Embry-Riddle Aeronautical University, Daytona BeachFollow
Taryn E. Trimble, Embry-Riddle Aeronautical University, Daytona BeachFollow
Eshna Bhargava, Embry-Riddle Aeronautical University, Daytona BeachFollow
Jake Klingler, Embry-Riddle Aeronautical University, PrescottFollow
Benjamin R. Nicolai, Embry-Riddle Aeronautical University, PrescottFollow

Faculty Mentor

Dr. Mihhail Berezovski, Dr. Christopher Briggs

Abstract

Flight time prediction plays a crucial role in modern air travel, benefiting airlines and passengers alike. Accurate predictions enable airlines to optimize schedules, allocate resources effectively, and ensure passenger safety and satisfaction. In recent years, machine learning models, such as neural networks and XGBoost, have gained popularity for predicting flight times. This study aims to compare the performance of neural network and XGBoost models in predicting flight times, considering factors such as weather conditions, air traffic control, and aircraft performance. The results indicate that both models are effective, with XGBoost achieving slightly higher accuracy. However, neural networks offer advantages in terms of computational efficiency and ease of interpretation. This study sheds light on the significance of flight time prediction and provides insights into the relative performance of neural network and XGBoost models in this domain.

Recommended Citation

Paraschos, Ioannis; Trimble, Taryn E.; Bhargava, Eshna; Klingler, Jake; and Nicolai, Benjamin R. (2025) "A Comparative Study of Neural Networks and XGBoost Models for Flight Time Prediction," Beyond: Undergraduate Research Journal: Vol. 8 , Article 3.
Available at: https://commons.erau.edu/beyond/vol8/iss1/3