PREDIKSI KECENDERUNGAN PELANGGAN UNTUK BERLANGGANAN DALAM E-COMMERCE MENGGUNAKAN METODE KNN BERBASIS PERILAKU TRANSAKSI

Amara Anastasya; Evi Morina  Br Tarigan; Salwa  Nabila; Michael  Ananda

doi:10.55338/jumin.v6i3.6461

Authors

Amara Anastasya, Universitas Satya Terra Bhinneka, Indonesia
Evi Morina Br Tarigan, Universitas Satya Terra BHinneka, Indonesia
Salwa Nabila, Universitas Satya Terra Bhinneka, Indonesia
Michael Ananda, Universitas Satya Terra Bhinneka, Indonesia

DOI:

https://doi.org/10.55338/jumin.v6i3.6461

Keywords:

prediksi langganan, e-commerce, K-Nearest Neighbor, perilaku transaksi, customer churn

Abstract

Penelitian ini bertujuan untuk memprediksi kecenderungan pelanggan untuk berlangganan layanan e-commerce dengan menerapkan algoritma K-Nearest Neighbor (KNN). Permasalahan customer churn yang berdampak pada keberlangsungan bisnis diatasi melalui pendekatan klasifikasi berbasis perilaku transaksi pelanggan. Dataset yang digunakan mencakup variabel seperti total pembelian, frekuensi transaksi, harga rata-rata, kategori produk, dan metode pembayaran. Untuk memecahkan masalah ini, data diproses melalui tahapan pembersihan, one-hot encoding, dan normalisasi min-max sebelum dibagi menjadi data latih (80%) dan uji (20%). Model KNN dikembangkan dengan nilai k = 5, dan dievaluasi menggunakan metrik akurasi, precision, recall, serta F1-score. Hasil menunjukkan akurasi 91%, precision 0,89, recall 0,87, dan F1-score 0,88, menegaskan efektivitas KNN dalam mengklasifikasikan pelanggan yang berpotensi churn. Fitur total pembelian dan frekuensi transaksi tercatat paling berpengaruh terhadap keputusan berlangganan. Temuan ini memberikan dasar bagi pengelola e-commerce untuk menyusun strategi retensi pelanggan yang lebih terarah, dengan memanfaatkan segmentasi serta penawaran yang dipersonalisasi. Penelitian ini juga menyoroti pentingnya kualitas data dan pemilihan parameter k yang tepat untuk meningkatkan performa prediksi.

Downloads

Download data is not yet available.

References

Statista, “Global e-commerce market size and forecast 2024,” Statista.com, 2024. [Online]. Available: https://www.statista.com/statistics/379046/worldwide-retail-e-commerce-sales/

V. Kumar and W. Reinartz, Customer Relationship Management: Concept, Strategy, and Tools, 3rd ed., Springer, 2018.

T. Chen, K. Fenyo, S. Yang, and J. Zhang, “Thinking inside the subscription box: New research on e-commerce consumers,” McKinsey & Company, Feb. 2018. [Online]. Available: https://www.mckinsey.com

S. Saad, “Comparative study of classification algorithms for customer behavior prediction,” Journal of Computer Science and Applications, vol. 7, no. 2, pp. 45–52, 2019.

Y. Liu and M. Shih, “Enhancing customer behavior prediction in e-commerce: A comparative analysis of machine learning and deep learning models,” Applied and Computational Engineering, vol. 55, pp. 181–195, 2024.

H. Zhang and L. Zheng, “Comparative analysis of machine learning algorithms for subscription prediction in e-commerce,” Journal of Artificial Intelligence Research, vol. 9, no. 3, pp. 112–120, 2021.

M. Alabdulwahab and R. Alotaibi, “Performance evaluation of machine learning models in customer subscription classification,” Middle East Journal of Computer and Information Sciences, vol. 12, no. 4, pp. 88–96, 2022.

A. Ramadhani, “Pengolahan data transaksi digital e-commerce untuk prediksi pelanggan,” Jurnal Teknologi dan Sistem Komputer, vol. 12, no. 1, pp. 33–40, 2024.

K. Matuszelański and K. Kopczewska, “Customer churn in retail e-commerce business: Spatial and machine-learning approach,” Journal of Theoretical and Applied Electronic Commerce Research, vol. 17, no. 1, pp. 165–198, 2022. doi: 10.3390/jtaer17010009.

S. Aggarwal and N. Kumar, “Evaluation of supervised machine learning algorithms for customer churn prediction in telecom sector,” Procedia Computer Science, vol. 167, pp. 377–386, 2020.

A. Tarasenko et al., “Customer behavior analysis using KNN and SVM classifiers,” Lecture Notes in Computer Science, vol. 12066, pp. 567–578, Springer, 2020.

S. Gupta and M. Dhankhar, “Optimizing K value in KNN for classification of high dimensional data,” International Journal of Advanced Research in Computer and Communication Engineering, vol. 9, no. 2, pp. 41–46, 2020.

N. Patel and D. Shrimankar, “Hybrid churn prediction model using machine learning algorithms,” Procedia Computer Science, vol. 171, pp. 2116–2124, 2020.

R. Fadhil, “Evaluasi model klasifikasi machine learning untuk churn pelanggan e-commerce,” Prosiding Seminar Nasional Teknologi Informasi dan Komunikasi (SENTIKA), vol. 11, pp. 101–108, 2023.

Python Software Foundation, “scikit-learn: Machine learning in Python,” Scikit-learn.org, 2024. [Online]. Available: https://scikit-learn.org/stable/

M. Sharda, S. Delen, and E. Turban, Analytics, Data Science, & Artificial Intelligence: Systems for Decision Support, 11th ed., Pearson Education, 2020.

D. Powers, “Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation,” Journal of Machine Learning Technologies, vol. 2, no. 1, pp. 37–63, 2015.

A. Kalgaonkar and N. Jadhav, “Application of machine learning to predict customer churn in e-commerce,” International Journal of Computer Applications, vol. 179, no. 25, pp. 8–14, 2020.

A. Singh and S. Kaur, “KNN classifier for churn prediction in telecom,” International Journal of Engineering and Technology, vol. 7, no. 2, pp. 70–74, 2018.

Google Developers, “Data preparation and feature engineering,” developers.google.com, 2023. [Online]. Available: https://developers.google.com/machine-learning/data-prep