| G. Vonitsanos, I. Gounaridis, A. Kanavos, Ph. Mylonas |
| Enhancing Aviation Efficiency through Big Data and Machine Learning for Flight Delay Prediction |
| 4th International Conference on Novel & Intelligent Digital Systems (NiDS 2024), September 25-27, 2024, Athens, Greece |
|
ABSTRACT
|
| Flight delays pose significant challenges to the aviation industry, leading to increased operational costs and passenger dissatisfaction. This paper explores the use of machine learning (ML) and big data analytics to enhance the accuracy and efficiency of flight delay predictions. Utilizing data from the Federal Aviation Administration (FAA) covering the period from 2018 to 2022, we analyze critical factors influencing delays and develop predictive models employing techniques such as Random Forest, Gradient Boosting Machines, Decision Trees, and k-Nearest Neighbors. Our analysis demonstrates that these ML techniques significantly outperform traditional models, improving the accuracy of delay predictions and thereby supporting airlines in optimizing operational efficiency and enhancing passenger satisfaction. The paper also discusses the practical implementation of these findings in real-time airline operations and outlines future research directions to further improve predictive accuracy.
|
| 25 September, 2024 |
| G. Vonitsanos, I. Gounaridis, A. Kanavos, Ph. Mylonas, "Enhancing Aviation Efficiency through Big Data and Machine Learning for Flight Delay Prediction", 4th International Conference on Novel & Intelligent Digital Systems (NiDS 2024), September 25-27, 2024, Athens, Greece |
[  PDF] [
BibTex] [
Print] [
 Back] |
