Data Mining for Airline Industry: Investigating satisfaction of airline passengers

Jadhav, Tejas Mahesh (2023) Data Mining for Airline Industry: Investigating satisfaction of airline passengers. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

In the robust competition of the aviation industry, passenger satisfaction plays a crucial role in the growth and success of an airline company. Air carriers that are able to identify and satisfy passenger demand stand out in the market with increased sales and more loyal customers. Passengers these days not only consider the ticket prices, but also scrutinize the quality of the airline services before selecting their carrier. Hence it is essential for the airline companies to provide quality services to their passengers. The feedback and reviews given by the passengers can act as a useful tool in understanding their service expectations and demands of the passengers. With the help of data mining techniques, airline companies can not only gauge the satisfaction of their passengers but also discover insights for improvising the services. Apart from conventional feedback forms, social media platforms like Twitter are becoming a popular choice among passengers to express their views and feedback on their travels. These feedbacks can also be used by the airline companies for understanding the sentiments of the passengers. To provide a direction on the same front, this study investigates the satisfaction of airline passengers by leveraging data mining techniques on two different datasets. The first dataset is a survey dataset consisting of satisfaction scores of 103903 airline passengers over different services of airline companies. The second dataset consists of 14641 tweets of the airline passengers. After evaluating 18 different classifiers on both the datasets, it was observed that Soft Voting Classifier is a better performing classifier for the first dataset and gives an accuracy of 96.60 percent. For the second dataset, the stacking classifier is a better performing classifier which showcased an accuracy of 93.98 percent. As for service attributes, in-flight Wi-Fi services and online boarding provision have a greater impact on passenger’s satisfaction, hence airline companies should focus on improving those services aspects. In addition, the ‘Type of Travel’ is also an important aspect of passenger’s satisfaction. Hence, the airline crew should behave accordingly with the passengers traveling for business or personal travel purposes.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Razzaq, Abdul UNSPECIFIED
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 H Social Sciences > HF Commerce > Marketing > Consumer Behaviour
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	18 May 2023 16:41
Last Modified:	18 May 2023 16:41
URI:	https://norma.ncirl.ie/id/eprint/6593

Actions (login required)

View Item