Beyond symmetric models: explaining satisfaction through AIPA and machine learning approaches in the airline industry

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

The airline industry is facing intense competition, where customer satisfaction (CS) is a critical determinant of long-term success. Therefore, it is essential to identify the critical factors that drive CS. Drawing on three-factor theory of CS, this study aims to examine the asymmetric effects of airline service attributes on CS. Moreover, the analysis also considers the segmentation between full-service carriers (FSCs) and low-cost carriers (LCCs). To achieve this, 8033 Skytrax reviews from 15 European airlines were analyzed using Asymmetric Impact-Performance Analysis (AIPA), further supported with advanced Machine Learning (ML) techniques to enhance explanatory power and identify key drivers of CS. The AIPA results reveal that the asymmetric effects of service attributes on CS may vary across different market segments. The ML results further demonstrate that value for money consistently emerges as the most influential determinant of CS, while ground service, cabin staff service, and seat comfort also play important roles. By combining asymmetric analysis with explainable machine learning, this study offers a clearer understanding of how passenger evaluations are formed and highlights the importance of maintaining consistent performance across key service touchpoints.