文章基本信息

标题：Creating a prediction model of passenger preference between low cost and legacy airlines
本地全文：下载
作者：Rian Mehta ; Stephen Rice ; John Deaton 等
期刊名称：Transportation Research Interdisciplinary Perspectives
印刷版ISSN：2590-1982
出版年度：2019
卷号：3
页码：1-10
DOI：10.1016/j.trip.2019.100075
出版社：Elsevier BV
摘要：The airline industry is highly competitive, and in order to increase profits, airlines are always looking to better target key customers. Increased understanding of customers also helps improve the product from the customer's perspective. This study aims to determine which factors predict airline passengers' preference between legacy and low-cost carriers. The correlational design used creates a prediction model for passengers from the United States. Through two stages of this study, 936 participants (379 females) from the US were utilized for the linear multiple regression analyses to build the model. In the first stage, the regression analysis was used to generate a regression model of passenger preference, which was then tested in the second stage, thereby validating the prediction model. Samples for each stage were independent and subjected to a backward stepwise regression analysis. To determine the influencers of passenger preference, nine potential predictors were surveyed. The predictors were age of the participant, gender of the participant, yearly income of the participant, education level of the participant, seat type, purpose of travel, frequency of travel in a year, category of frequent flier program, and risk-taking tendencies of the participant. The results of the data analysis showed frequency of travel in a year, yearly income of the participant, seat type, and education level of the participant as significant predictors of passengers' preference between legacy and low-cost carriers. This research has practical implications for the airline industry in better understanding the consumer base, which could lead to increased profitability for the carriers.
关键词：Legacy carriers ; Low-cost carriers ; Passenger preference ; Prediction model