|
AUTHOR(S): Jonah Gonzalo
|
TITLE Predicting Airline Passenger Satisfaction using Deep Learning |
 PDF |
ABSTRACT This paper aims to evaluate the performance of predictive algorithms for the prediction of flight passenger satisfaction. Naive Bayes, Logistic Regression, Deep Learning, Decision Trees, Random Forest, and Support Vector Machine were simulated using Invistico Airline datasets. The six predictive algorithms were tested and evaluated based on accuracy, classification error, accuracy, Precision, Recall, F-measure, sensitivity, specificity, and ROC-AUC comparison. Deep Learning has the highest accuracy at 93%, Gains at 28,406, and training time at 21ms. Arrival Delay in Minutes and Customer Type causes dissatisfaction while Departure Delay Time, Baggage Handling, Ease of Online Booking, and Inflight Entertainment are the predictors for flight satisfaction. The results of this study can be used as a guide for managers to understand their customers, determine the factors to enhance passenger satisfaction, improve airline service quality, and formulate numerous alternatives. |
KEYWORDS Flight Passenger Satisfaction, Data Analytics, Artificial Intelligence, Airline Management |
|
Cite this paper Jonah Gonzalo. (2025) Predicting Airline Passenger Satisfaction using Deep Learning. International Journal of Computers, 10, 138-150 |
|
