Prediction of Customer Satisfaction using Machine Learning Algorithms: Perspectives of Service and Operational Factors in Airline Industry

Customer satisfaction in the airline industry is influenced by demographic, service-related, and operational factors. As competition grows and passenger expectations evolve, understanding these determinants is crucial for improving service quality and loyalty. This study uses machine learning algorithms to analyze key drivers of customer satisfaction and derive actionable insights. It employs techniques such as Logistic Regression, Gaussian Naive Bayes, Gradient Boosting, K-Nearest Neighbors, and Random Forest classifiers. Among these, Gradient Boosting and Random Forest achieved the highest predictive accuracy, with AUC scores of 0.99 and 0.9937. A strong correlation (0.97) between departure and arrival delays highlights the importance of punctuality. Inflight services like entertainment and legroom, especially on long-haul flights, significantly enhance satisfaction. Demographic analysis shows passengers aged 40+ report higher satisfaction, emphasizing the need for tailored service strategies, while younger passengers (20-40) show lower satisfaction, indicating a need for personalized engagement. These findings provide a data-driven foundation for improving airline operations and service delivery. Future research should integrate real-time data for more adaptive service improvements.