Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Multidiciplinary Output Research for Actual and International Issue (Morfai Journal)
Kevin Benedicta
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Social Sciences Other

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

Found 1 Documents
Search

 1 
COMPARATIVE ANALYSIS OF TREE-BASED ALGORITHMS FOR CUSTOMER SATISFACTION CLASSIFICATION IN THE LOGISTICS INDUSTRY: A CASE STUDY OF JNE AND J&T EXPRESS Kevin Benedicta; Rudi Nurdiansyah
Multidiciplinary Output Research For Actual and International Issue (MORFAI) Vol. 6 No. 3 (2026): Multidiciplinary Output Research For Actual and International Issue
Publisher : RADJA PUBLIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The rapid growth of Indonesia’s e-commerce sector has intensified competition within the logistics industry, positioning customer satisfaction as a critical determinant of competitive advantage. However, the multidimensional and non-linear nature of service quality complicates traditional statistical analysis. This study aims to compare the performance of three tree-based machine learning algorithms (Decision Tree, Random Forest, and Gradient Boosting) in classifying customer satisfaction for JNE and J&T Express, while identifying the key service quality dimensions driving satisfaction. Using a validated dataset of 408 respondents, individual service indicators are modeled as predictive features. Hyperparameter tuning is conducted through 500-iteration Randomized Search with 5-fold cross-validation. The results show that the Decision Tree achieves the highest performance for the JNE dataset with an accuracy of 78.05%, precision of 79.16%, recall of 78.05%, and an F1-score of 77.84%. In contrast, Gradient Boosting outperforms other models for the J&T Express dataset with an accuracy of 81.71%, precision of 81.69%, recall of 81.71%, and an F1-score of 81.37%. Furthermore, Feature Importance analysis consistently identifies Shipping Cost as the dominant predictor of satisfaction. These findings highlight the efficacy of tree-based machine learning in decoding complex satisfaction patterns, offering actionable, data-driven insights for logistics service providers.
Co-Authors Nurdiansyah Rudi