Penerapan Algoritma XGBoost Untuk Prediksi Kepuasan Pelanggan Pada Layanan E-Commerce: Studi Pada Dataset Transaksi Nyata

Dhimas Tribuana; Baharuddin Baharuddin; Andi Muhammad Resky

doi:10.64476/jtbc.v1i1.5

Penulis

Dhimas Tribuana Universitas Komputer Indonesia
Baharuddin Baharuddin Fakultas Ilmu Komputer, Universitas Ichsan Sidenreng Rappang, Sidrap
Andi Muhammad Resky Fakultas Teknik, Universitas Muhammadiyah Parepare, Parepare

DOI:

https://doi.org/10.64476/jtbc.v1i1.5

Kata Kunci:

Kepuasan Pelanggan, E-Commerce, Machine Learning, XGBoost, Prediksi

Abstrak

Pertumbuhan e-commerce di Indonesia yang pesat memunculkan tantangan baru bagi penyedia layanan untuk menjaga kepuasan pelanggan di tengah kompetisi yang semakin ketat. Penelitian ini bertujuan untuk mengembangkan model prediktif berbasis Extreme Gradient Boosting (XGBoost) dalam memprediksi kepuasan pelanggan e-commerce dengan memanfaatkan dataset nyata berskala besar. Dataset yang digunakan berasal dari Kaggle (E-Commerce Customer Satisfaction) yang mencakup lebih dari 100.000 transaksi dengan atribut seperti harga, biaya pengiriman, waktu pengiriman, serta ulasan pelanggan. Data diproses melalui tahapan pembersihan, encoding, normalisasi, dan feature engineering. Model XGBoost dibandingkan dengan Random Forest dan Logistic Regression untuk mengevaluasi performa prediksi. Hasil eksperimen menunjukkan bahwa XGBoost mencapai akurasi 92,4%, F1-score 90,6%, dan ROC-AUC 0,941, mengungguli kedua model pembanding. Analisis feature importance dan SHAP mengidentifikasi bahwa review score, freight value, dan delivery delay merupakan faktor dominan yang mempengaruhi kepuasan pelanggan. Temuan ini memiliki implikasi praktis bagi pelaku e-commerce untuk mengoptimalkan strategi logistik dan layanan pasca-pembelian dalam meningkatkan pengalaman pelanggan. Penelitian ini juga menekankan pentingnya pemanfaatan machine learning dalam pemantauan kepuasan secara real-time dan memberikan kontribusi bagi literatur ilmu data di bidang e-commerce Indonesia.

Unduhan

Data unduhan belum tersedia.

Referensi

Abdullah-All-Tanvir, Ali Khandokar, I., Muzahidul Islam, A. K. M., Islam, S., & Shatabda, S. (2023). A gradient boosting classifier for purchase intention prediction of online shoppers. Heliyon, 9(4), e15163. https://doi.org/10.1016/j.heliyon.2023.e15163

Andy Hermawan, Aji Saputra, Muhammad Dhika Rafi, Syafiq Basmallah, Yilmaz Trigumari Syah Putra, & Wafa Nabila. (2025). Implementing XGBoost Model for Predicting Customer Churn in E-Commerce Platforms. Repeater : Publikasi Teknik Informatika Dan Jaringan, 3(2), 17–31. https://doi.org/10.62951/repeater.v3i2.401

Cai, K., & Rodavia, M. R. (2023). XGBoost Analysis based on Consumer Behavior. Frontiers in Computing and Intelligent Systems, 5(2), 85–89. https://doi.org/10.54097/fcis.v5i2.12974

Chen, T., & Guestrin, C. (2016). XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785

Gregory, B. (2018). Predicting Customer Churn: Extreme Gradient Boosting with Temporal Data. https://arxiv.org/abs/1802.03396

Guan, G., Liu, D., & Zhai, J. (2022). Factors Influencing Consumer Satisfaction of Fresh Produce E-Commerce in the Background of COVID-19—A Hybrid Approach Based on LDA-SEM-XGBoost. Sustainability, 14(24), 16392. https://doi.org/10.3390/su142416392

Le, H.-S., Do, T.-V. H., Nguyen, M. H., Tran, H.-A., Pham, T.-T. T., Nguyen, N. T., & Nguyen, V.-H. (2024). Predictive model for customer satisfaction analytics in E-commerce sector using machine learning and deep learning. International Journal of Information Management Data Insights, 4(2), 100295. https://doi.org/10.1016/j.jjimei.2024.100295

Lundberg, S. M. , & Lee, S. I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems 30. https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf

Maylinda, W. D., & Andarini, S. (2024). Pengaruh Customer Experience Dan Personalisasi Artificial Intelligence (AI) Terhadap Loyalitas Konsumen E-Commerce Shopee Di Surabaya. Journal of Economic, Bussines and Accounting (COSTING), 7(3), 6039–6048. https://doi.org/10.31539/costing.v7i3.9569

Nico, H., La, M., Mustika, J., Ruth, J., & Z., H. (2022). Factors Affecting Online Purchase Decision, Customer Satisfaction, and Brand Loyalty: An Empirical Study from Indonesia’s Biggest E-Commerce. The Journal of Distribution Science, 20(11). https://doi.org/https://doi.org/10.15722/jds.20.11.202211.33

Olist. (2018). Brazilian E-Commerce Public Dataset by Olist. Olist. https://www.kaggle.com/datasets/olistbr/brazilian-ecommerce

Pahlevi, R. (2022). Nilai Transaksi E-Commerce Indonesia Diperkirakan Capai US$137,5 Miliar pada 2025. https://databoks.katadata.co.id/teknologi-telekomunikasi/statistik/578053fb8bceef8/nilai-transaksi-e-commerce-indonesia-diperkirakan-capai-us1375-miliar-pada-2025

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12(85), 2825–2830. http://jmlr.org/papers/v12/pedregosa11a.html

Sondakh, D. E., Taju, S., Regina Patricia, & Tumbal, R. (2024). Sentiment Analysis of Customer Satisfaction of Shopee Service Quality. 11th International Scholars Conference, 11(5), 1463–1472. https://doi.org/10.35974/isc.v11i5.3574

Song, P., & Liu, Y. (2020). An XGBoost Algorithm for Predicting Purchasing Behaviour on E-Commerce Platforms. Tehnicki Vjesnik - Technical Gazette, 27(5). https://doi.org/10.17559/TV-20200808113807

Suastiari, N. K. S., & Mahyuni, L. P. (2022). DETERMINANTS OF E-COMMERCE USER SATISFACTION: THE MEDIATING ROLE OF PURCHASE INTENTION. Jurnal Ekonomi Bisnis Dan Kewirausahaan, 11(3), 345. https://doi.org/10.26418/jebik.v11i3.56329

Wang, M., Liu, Y., Li, G., Payne, T. R., Yue, Y., & Man, K. L. (2024). Unlocking Your Sales Insights: Advanced XGBoost Forecasting Models for Amazon Products. https://arxiv.org/abs/2411.00460

Wilson, N., & Christella, R. (2019). An Empirical Research of Factors Affecting Customer Satisfaction: A Case of the Indonesian E-Commerce Industry. DeReMa (Development Research of Management): Jurnal Manajemen, 14(1), 21. https://doi.org/10.19166/derema.v14i1.1108

Zhang, J. (2025). Enhancing Predictive Models in E-Commerce: A Comparative Study Using XGBoost Across Diverse Scenarios. ITM Web of Conferences, 70, 02014. https://doi.org/10.1051/itmconf/20257002014