Flight delays significantly affect airlines, passengers, and overall airport efficiency, making accurate delay prediction a vital area of research. This study adopts machine learning techniques to develop predictive models for flight delays by analysing diverse factors, including historical flight records, weather conditions, airline operations, and airport congestion. By integrating advanced algorithms such as regression models, decision trees, ensemble techniques, and deep learning frameworks, the research aims to identify the key contributors to delays and improve prediction accuracy. Extensive feature selection and pre-processing methods are applied to optimize the predictive capabilities of the models. Results indicate that ensemble deep learning approaches achieve superior performance compared to the traditional techniques. These findings emphasize the potential of machine learning approach in addressing real-world challenges in aviation by enabling more efficient scheduling and resource management. This research provides a foundation for future innovations in minimizing disruptions and enhancing the passenger experience.
Accurate Flight Delay Prediction Using Machine Learning Techniques
2025-06-25
506367 byte
Conference paper
Electronic Resource
English
Flight Delay Prediction using Machine Learning Model
IEEE | 2022
|Flight Arrival Delay Prediction Using Supervised Machine Learning Algorithms
Springer Verlag | 2021
|Flight delay prediction based on machine learning method
SPIE | 2024
|