Predicting Flight Delays: How Weather and Seasons Affect Air Travel?

Guru, Aniket (2023) Predicting Flight Delays: How Weather and Seasons Affect Air Travel? Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This study presents a comparative analysis of LSTM and Random Forest classifiers in predicting flight delays at JFK International Airport, incorporating weather and holiday data for enhanced prediction accuracy. The research demonstrates the efficacy of a 5-class classification system over traditional regression models. The classification approach effectively handles imbalanced data and outliers, offering interpretable insights into delay causatives. The Random Forest model slightly outperforms LSTM with an overall accuracy of 0.9239 in case of unsampled data, while LSTM excels in precision and F1-scores for certain delay classes. Key findings underscore the significant impact of weather, particularly precipitation and wind gusts, on flight delays, with notable disruptions during peak travel seasons. These results equip airlines and aviation authorities with actionable insights to mitigate delays, optimize operations, and improve passenger experience. The novel inclusion of holiday data alongside weather variables in the predictive models contributes to the broader understanding of flight delay factors, paving the way for more informed decision-making in the aviation industry.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Agrawal, Bhart UNSPECIFIED
Uncontrolled Keywords:	LSTM Classifier; Random Forest Classifier; Accuracy; F1-Score
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Aviation Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	08 May 2025 14:41
Last Modified:	08 May 2025 14:41
URI:	https://norma.ncirl.ie/id/eprint/7521

Actions (login required)

View Item