ANALISIS SIMULASI PREDIKSI CUSTOMER CHURN E-COMMERCE MENGGUNAKAN ALGORITMA RANDOM FOREST BERBASIS DATA SINTETIS
DOI:
https://doi.org/10.35794/jmbi.v13i1.67545Abstract
Tingkat customer churn yang tinggi menjadi tantangan kritis bagi industri e-commerce di Indonesia dengan potensi kerugian mencapai miliaran rupiah per tahun. Penelitian ini bertujuan untuk mengimplementasikan sistem prediksi churn pelanggan sebagai proof-of-conceptmenggunakan algoritma machine learning. Mengingat keterbatasan akses data privat e-commerce, penelitian ini menggunakan pendekatan metodologis dengan dataset sintetis yang terdiri dari 1000 data pelanggan dan 9 fitur utama meliputi tenure, monthly spending, total transactions, support tickets, dan last purchase days. Tiga algoritma machine learning diimplementasikan yaitu Logistic Regression, Decision Tree, dan Random Forest untuk melakukan klasifikasi prediksi churn. Hasil penelitian menunjukkan bahwa Random Forest memberikan performa yang paling stabil dengan akurasi sebesar 87.5%, precision 86%, recall 87%, dan F1-score 86%. Penurunan performa dibandingkan model deterministik menunjukkan bahwa model diuji pada kondisi data yang lebih realistis dan tidak mengalami overfitting terhadap aturan generatif.
References
Ahmad, A. K., Jafar, A., & Aljoumaa, K. (2019). Customer churn prediction in telecom using machine learning in big data platform. Journal of Big Data, 6(1), 1–24.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794).
De Caigny, A., Coussement, K., & De Bock, K. W. (2020). A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees. European Journal of Operational Research, 269(2), 760–772.
García, S., Luengo, J., & Herrera, F. (2020). Data preprocessing in data mining. Springer.
Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O’Reilly Media.
Kumar, R., & Sharma, P. (2022). A comprehensive study on customer churn prediction in e-commerce using ML techniques. International Journal of Information Technology, 14(5), 2567–2580.
Lalwani, P., Mishra, M. K., Chadha, J. S., & Sethi, P. (2022). Customer churn prediction system: A machine learning approach. Computing, 104(2), 271–294.
Lazarov, S., & Capota, M. (2023). Churn prediction in e-commerce using machine learning and ensemble methods. IEEE Access, 11, 45789–45801.
Óskarsdóttir, M., Bravo, C., Verbeke, W., Sarraute, C., Baesens, B., & Vanthienen, J. (2021). Social network analytics for churn prediction in telco: Model building, evaluation and network architecture. Expert Systems with Applications, 184, Article 115508.
Provost, F., & Fawcett, T. (2023). Data science for business: What you need to know about data mining and data-analytic thinking. O’Reilly Media.
Saghir, M., Bibi, Z., Bashir, S., & Khan, F. H. (2019). Churn prediction using neural network based individual and ensemble models.
Striuk, V., & Ternov, O. (2021). Customer churn prediction for e-commerce using machine learning algorithms.
Verbraken, W., Bravo, C., Weber, R., & Baesens, B. (2014). Development and application of consumer credit scoring models using profit-based classification measures. European Journal of Operational Research, 238(2), 505–513.
Zhang, Y., & Qi, Y. (2020). Customer churn prediction in e-commerce based on deep learning.
