A Machine Learning Approach Predicting Flight Arrival Delay Reduction for Delta Airlines

Enwere, Chibuike Kenneth (2019) A Machine Learning Approach Predicting Flight Arrival Delay Reduction for Delta Airlines. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (662kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

The efficiency of the air transport system has been attributed to it been the fastest means of transportation, which has over the years gained strong reliability from customers, however flight arrival delays have become imperative in the airline industry as delays in this phase of the flight depends on the organization of the airspace and runway availability. Cancellation and diversion of flights due to either air traffic operational short comings or unforeseen circumstances such as weather brings bad reputation to airlines and unnecessary expense due to reimbursement of customers. This research work was focused on analysing the arrival delay of domestic flights operated by Delta airlines in the United States using several supervised machine learning algorithms which includes Gradient Boosting Classifier, Decision trees, Naïve Bayes, Support Vector Machine, Random forest and logistic regression, while comparing their performance based on Accuracy, Precision, Recall and Specificity in order to find models with the best accuracy. Each predictive model was trained by collecting data from the Bureau of transport statistics (BTS), and the data contained Delta airlines operated flights for the year 2017 while using feature selection to get relevant attributes used in the analysis. The gradient boosting classifier showed the best accuracy of 70% as compared to other models. This research will provide insights to Delta airlines by shedding light on different aspects where flight arrival delays can be improved.
Keywords: Random Forest, Gradient boosting classifier, Flight Arrival Delay, Delta airlines, Support vector classifier, logistic regression, Naïve Bayes

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software T Technology > TL Motor vehicles. Aeronautics. Astronautics H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Aviation Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	17 Jun 2020 17:02
Last Modified:	17 Jun 2020 17:02
URI:	https://norma.ncirl.ie/id/eprint/4305

Actions (login required)

View Item