Enhancing airport services: data-driven analysis of passenger satisfaction and service quality in Southeast Asia

Pholsook Thitinan (), Ramjan Sarawut () and Wipulanusat Warit ()
Additional contact information
Pholsook Thitinan: Thammasat University, Bangkok, 10200, Thailand
Ramjan Sarawut: Suranaree University of Technology, Nakhon Ratchasima, 30000, Thailand
Wipulanusat Warit: Thammasat University, Pathumthani, 12120, Thailand

Engineering Management in Production and Services, 2025, vol. 17, issue 2, 37-62

Abstract: Airports encompass a range of service touchpoints that directly impact passenger satisfaction and, consequently, the likelihood of service recommendation. This study investigates the service quality of Southeast Asian airports by applying five supervised machine learning classification models — decision trees, random forests, support vector machines, neural networks, and gradient boosting machines — on passenger satisfaction data extracted from the Skytrax website. The dataset includes evaluations of various service dimensions, such as staff behaviour, queuing time, and overall experience. This study incorporates cross-validation and hyperparameter tuning to identify the most suitable model for classifying passenger satisfaction. Among the models tested, the random forest classifier achieved the highest accuracy (0.91), demonstrating strong robustness and interpretability. Model performance was assessed using confusion matrices, balanced accuracy, the Matthews correlation coefficient (MCC), and ROC curves. Furthermore, SHAP values were used to identify the most influential service touchpoints, highlighting airport staff performance and queue management as key factors. These findings align with existing literature emphasising the pivotal role of well-trained airport employees and efficient queuing systems in shaping positive passenger experiences. Studies have shown that courteous staff interactions, efficient conflict resolution, and reduced waiting times significantly contribute to customer satisfaction and loyalty. Additionally, the integration of smart technologies such as self-service kiosks, automated security systems, and touchless check-in and baggage solutions enhances operational efficiency and aligns with sustainability initiatives. This study offers a data-driven approach for airport managers to optimise service delivery, increase passenger experiences, and tailor improvements to specific airport environments.

Keywords: airport quality service; machine learning; data classification; hyperparameter tuning (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.2478/emj-2025-0011 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:vrs:ecoman:v:17:y:2025:i:2:p:37-62:n:1003

DOI: 10.2478/emj-2025-0011

Access Statistics for this article

Engineering Management in Production and Services is currently edited by Joanna Ejdys

More articles in Engineering Management in Production and Services from Sciendo
Bibliographic data for series maintained by Peter Golla ().