MENERAPKAN DATA SCIENCE PADA DATASET REVIEW PRODUK DI SHOPEE DAN TOKOPEDIA: PENGELOMPOKAN PELANGGAN DAN STRATEGI RETENSI DENGAN TEKNIK CLUSTERING

Yogo Turnandes, Rezka Afrilli

Abstract


Abstract: This study employs data science methodologies to analyze product reviews from the e-commerce sites Shopee and Tokopedia. The primary objective is to segment customers by grouping them according to their review patterns using clustering methods. The aim is to create customized retention strategies for each segment. The research applies K-Means clustering to group customers based on their product ratings, frequency of reviews, and sentiment analysis scores. The number of optimal clusters is determined through the Elbow Method, while the clustering performance is assessed using the Silhouette Score. Furthermore, Principal Component Analysis (PCA) is used to visualize the customer clusters in two dimensions. The findings reveal significant customer insights and provide a basis for developing tailored retention strategies to improve customer loyalty and satisfaction.

 

Keywords: Data Science; Customer Segmentation; Clustering Techniques; K-Means Algorithm; Retention Strategies

 

Abstrak: Penelitian ini menggunakan metodologi data science untuk menganalisis ulasan produk dari situs e-commerce Shopee dan Tokopedia. Tujuan utama dari penelitian ini adalah untuk mengelompokkan pelanggan berdasarkan pola ulasan mereka menggunakan metode clustering. Penelitian ini bertujuan untuk merancang strategi retensi yang disesuaikan dengan masing-masing segmen pelanggan. Dengan menggunakan algoritma K-Means, pelanggan dikelompokkan berdasarkan rating produk, frekuensi ulasan, dan skor sentimen. Jumlah klaster optimal ditentukan melalui Metode Elbow, sementara kinerja pengelompokan dinilai dengan menggunakan Silhouette Score. Selain itu, Principal Component Analysis (PCA) digunakan untuk memvisualisasikan segmen pelanggan dalam dua dimensi. Temuan dari penelitian ini memberikan wawasan penting tentang perilaku pelanggan dan menjadi dasar untuk mengembangkan strategi retensi yang lebih terarah guna meningkatkan loyalitas dan kepuasan pelanggan.

 

Kata kunci: Data Science; Segmentasi Pelanggan; Teknik Clustering; Algoritma K-Means; Strategi Retensi


Full Text:

PDF

References


Bandyopadhyay, S., Thakur, S. S., & Mandal, J. K. (2021). Product recommendation for e-commerce business by applying principal component analysis (PCA) and K-means clustering: Benefit for the society. Innovative Systems and Soft Computing, 17(1), 45–52.

Mwencha, P. M., & Muathe, S. M. (2024). Enhancing online retail insights: K-Means clustering and PCA for customer segmentation. Journal of Retailing and Consumer Services, 58, 102-110.

Nugroho, B. I. (2024). Customer segmentation in sales transaction data using K-Means clustering algorithm. Journal of Intelligent Decision Support System, 7(2), 130–136.

Tabianan, K., Velu, S., & Ravi, V. (2022). K-Means Clustering Approach for Intelligent Customer Segmentation Using Customer Purchase Behavior Data. Sustainability, 14(12), 7243.

MacQueen, J. (1967). Some Methods for Classification and Analysis of Multivariate Observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1, 281-297.

Li, X. (2017). The Impact of Big Data Analytics on E-Commerce: A Literature Review. International Journal of Information Technology and Management, 16(2), 123-145.

Chen, M., Mao, S., & Liu, Y. (2020). Big Data: A Survey. Mobile Networks and Applications, 25(3), 1-11.

Jain, A. K. (2010). Data Clustering: 50 Years Beyond K-Means. Pattern Recognition Letters, 31(8), 651-666.

Cheng, X., Yang, C., & Xie, K. (2019). A Survey of Customer Review Mining for E-Commerce. Information Systems Frontiers, 21(5), 1-18.

Huang, J., Liu, T., & Zhang, Y. (2021). E-Commerce Customer Segmentation Based on Behavioral Data Mining. International Journal of Computer Science and Information Security, 19(5), 92-105.

Yu, L., & Jiang, Y. (2022). Customer Segmentation and Retention Strategy for E-Commerce Based on K-Means Clustering and Market Basket Analysis. Journal of Business Research, 69(12), 5435-5443.

Wu, X., & Ding, Z. (2023). A Comparative Study of Customer Segmentation Methods in E-Commerce: K-Means, DBSCAN, and Agglomerativ.e Clustering. Computational Intelligence and Neuroscience, 2023, 1-15




DOI: https://doi.org/10.54314/jssr.v8i3.4067

Article Metrics

Abstract view : 180 times
PDF - 52 times

Copyright (c) 2025 Rezka Afrilli

Jurnal Goretan Pena