Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Information System Exploration and Research
Anggyi Trisnawan Putra
Department of Computer Science, Universitas Negeri Semarang, Indonesia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Interpretable Airline Passenger Satisfaction Prediction Using Recursive Feature Elimination, Bayesian-Optimized Random Forest, and SHAP Arrijalu Ringga Fahreza; Anggyi Trisnawan Putra
Journal of Information System Exploration and Research Vol. 4 No. 4: October 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i4.119

Abstract

Airline passenger satisfaction prediction can assist service-quality planning, but accurate classification alone does not explain model decisions. This study evaluates four Random Forest (RF) configurations with and without Recursive Feature Elimination (RFE) and Bayesian Optimization, complemented by SHapley Additive exPlanations (SHAP). A publicly used airline satisfaction dataset comprising 129,880 records and 25 original columns was examined. Following removal of two identifiers and the target, 22 candidate predictors remained. Stratified training–testing division (80:20) and training-only preprocessing were used to prevent data leakage. The four models achieved respective test accuracies of 94.67% (RF), 94.60% (RF+RFE), 96.25% (RF + Bayesian Optimization), and 95.82% (RF+RFE+Bayesian Optimization). The integrated model retained 15 predictors and achieved 96.64% precision, 93.65% recall, 95.12% F1-score, and 0.9927 ROC-AUC. Sensitivity analysis over 10–20 predictors identified a higher cross-validation accuracy at 18 features (96.30%) than at 15 (95.73%); 15 features were retained as a compact, predefined subset, not an accuracy-optimal solution. Positive-class SHAP explanations identified Type of Travel, Inflight WiFi Service, Online Boarding, Class, and Customer Type as leading contributors in a 300-observation test sample. The findings support an interpretable feature-reduction and predictive-performance trade-off without claiming that the integrated model maximizes accuracy or establishes causal service effects.
Co-Authors Arrijalu Ringga Fahreza