Table of Content

Open Access iconOpen Access



Flight Delay Prediction Using Gradient Boosting Machine Learning Classifiers

Mingdao Lu, Peng Wei, Mingshu He*, Yinglei Teng

Beijing University of Posts and Telecommunications, Beijing, 100876, China

* Corresponding Author: Mingshu He. Email: email

Journal of Quantum Computing 2021, 3(1), 1-12.


With the increasing of civil aviation business, flight delay has become a key problem in civil aviation field in recent years, which has brought a considerable economic impact to airlines and related industries. The delay prediction of specific flights is very important for airlines’ plan, airport resource allocation, insurance company strategy and personal arrangement. The influence factors of flight delay have high complexity and non-linear relationship. The different situations of various regions and airports, and even the deviation of airport or airline arrangement all have certain influence on flight delay, which makes the prediction more difficult. In view of the limitations of the existing delay prediction models, this paper proposes a flight delay prediction model with more generalization ability and corresponding machine learning classification algorithm. This model fully exploits temporal and spatial characteristics of higher dimensions, such as the influence of preceding flights, the situation of departure and landing airports, and the overall situation of flights on the same route. In the process of machine learning, the model is trained with historical data and tested with the latest actual data. The test result shows that the model and this machine learning algorithm can provide an effective method for the prediction of flight delay.


Cite This Article

M. Lu, P. Wei, M. He and Y. Teng, "Flight delay prediction using gradient boosting machine learning classifiers," Journal of Quantum Computing, vol. 3, no.1, pp. 1–12, 2021.


cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 2011


  • 1302


  • 2


Share Link