Designing Predictive Models for Customer Recommendations During COVID-19 in the Airline Industry

Lee, Carmen Kar Hang ORCID: 0000-0001-8878-939X and Leung, Eric Ka Ho ORCID: 0000-0003-2058-0287 (2024) Designing Predictive Models for Customer Recommendations During COVID-19 in the Airline Industry. IEEE Transactions on Engineering Management, PP (99). pp. 1-11.

Text
TEM-Eric-author accepted version.pdf - Author Accepted Manuscript
Download (937kB) | Preview

Official URL: http://dx.doi.org/10.1109/tem.2022.3211767

Abstract

Although travel restrictions imposed by countries are gradually lifted, the airline industry rebounds only when customers’ confidence in air travel is restored. Airlines that generate positive customer recommendations during the pandemic can have a competitive advantage in the post-pandemic environment. This article focuses on the prediction of customer recommendations of airlines during the pandemic. The results show that airline ratings established before the pandemic have weak performance, implying that customer recommendations could be based on other factors that are unique to the pandemic. In addition, COVID-19 travel safety of airlines and sentiments hidden in customer reviews are valuable for predicting customer recommendations. The results also confirm that flight duration affects the predictive powers of airline rating established before the pandemic and COVID-19 travel safety rating of airlines. There are important implications for the airline industry. First, airline ratings established before pandemic is not valuable to predict customer recommendations during COVID-19, underpinning the importance of including COVID-19 travel safety measures as part of the airline evaluation criteria in the future. Besides, COVID-19 travel safety is more relevant to customer recommendations in the long-haul markets. When selecting airlines for evaluation, airline rating organizations can give priorities to airlines that offer long-haul flights.

Item Type:	Article
Additional Information:	(c) 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Depositing User:	Symplectic Admin
Date Deposited:	03 Oct 2022 07:51
Last Modified:	17 Mar 2024 15:17
DOI:	10.1109/tem.2022.3211767
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3165109