Hybrid Clustering and Classification of At-Risk Customer Segments in Network Marketing

Main Article Content

Unung Istopo Hartanto
I Gusti Putu Asto Buditjahjanto
Wiyli Yustanti

Abstract

Customer segmentation is a fundamental strategy for sustaining retention in network marketing businesses, where repeated transactions and multilayered relationships significantly impact long-term customer value. This study proposes a hybrid machine learning framework to classify at-risk customer segments—comprising regular customers, seasonal buyers, and churn-risk profiles—by integrating unsupervised clustering and supervised classification methods. A total of 36 engineered behavioral features were derived from longitudinal transaction data to capture spending behavior, recency, variability, and growth dynamics. Clustering algorithms including K-Means, Agglomerative Hierarchical Clustering, and Gaussian Mixture Models were applied and evaluated using standard clustering validity indices: Silhouette Score, Davies–Bouldin Index, and Calinski–Harabasz Index. K-Means with six clusters produced the most interpretable and balanced segmentation outcome. Cluster relabeling was conducted to align with business-relevant categories, followed by supervised validation using classifiers such as Decision Tree, Gradient Boosting, K-Nearest Neighbors (KNN), Random Forest and Support Vector Machine (SVM). Among these, SVM yielded the highest predictive accuracy (92.53%) and F1-Score (92.52). The results demonstrate the effectiveness of the proposed hybrid approach in enhancing segmentation precision and facilitating early detection of potential churn in a dynamic marketing environment.

Article Details

Section
Articles

References

[1] (2024) Annual Report – wfdsa. [Online], https://wfdsa.org/2024-annual-report/, accessed May 31, 2025.

[2] APLI | Asosiasi Penjualan Langsung Indonesia (2025),” Asosiasi Penjualan Langsung Indonesia, 2025. [Online], https://www.apli.or.id/news/10-pilar-penting-agar-perusahaan-ds-mlm-sukses-di-indonesia-tahun-202589, accessed May 31, 2025.

[3] E. Eslami, N. Razi, M. Lonbani, and J. Rezazadeh, “Unveiling IoT Customer Behaviour: Segmentation and Insights for Enhanced IoT-CRM Strategies: A Real Case Study,” Sensors, vol. 24, no. 4, p. 1050, Jan. 2024, doi: https://doi.org/10.3390/s24041050.

[4] Y. Sun and X. Tan, “Customer Relationship Management Based on SPRINT Classification Algorithm under Data Mining Technology,” Computational Intelligence and Neuroscience, vol. 2022, p. 6170335, Apr. 2022, doi: https://doi.org/10.1155/2022/6170335.

[5] B. Nguyen and D. S. Mutum, “A review of customer relationship management: successes, advances, pitfalls and futures,” Business Process Management Journal, vol. 18, no. 3, pp. 400–419, Jun. 2012, doi: https://doi.org/10.1108/14637151211232614.

[6] K. Kim, M. Jo, I. Ra, and S. Park, “RFMVDA: An Enhanced Deep Learning Approach for Customer Behavior Classification in E-Commerce Environments,” IEEE Access, pp. 1–1, Jan. 2025, doi: https://doi.org/10.1109/access.2025.3529023.

[7] W. Verbeke, D. Martens, and B. Baesens, “Social network analysis for customer churn prediction,” Applied Soft Computing, vol. 14, pp. 431–446, Jan. 2014, doi: https://doi.org/10.1016/j.asoc.2013.09.017.

[8] P. Boozary, S. Sheykhan, H. GhorbanTanhaei, and C. Magazzino, “Enhancing customer retention with machine learning: A comparative analysis of ensemble models for accurate churn prediction,” International Journal of Information Management Data Insights, vol. 5, no. 1, p. 100331, Feb. 2025, doi: https://doi.org/10.1016/j.jjimei.2025.100331.

[9] C.-Y. . Tsai and C.-C. . Chiu, “A purchase-based market segmentation methodology,” Expert Systems with Applications, vol. 27, no. 2, pp. 265–276, Aug. 2004, doi: https://doi.org/10.1016/j.eswa.2004.02.005.

[10] P. S. Fader, B. G. S. Hardie, and K. L. Lee, “RFM and CLV: Using Iso-Value Curves for Customer Base Analysis,” Journal of Marketing Research, vol. 42, no. 4, pp. 415–430, Nov. 2005, doi: https://doi.org/10.1509/jmkr.2005.42.4.415.

[11] J. B. MacQueen, “Some methods for classification and analysis of multivariate observations,” vol. 1, pp. 281–297, Jan. 1967.

[12] [12] E. W. T. Ngai, L. Xiu, and D. C. K. Chau, “Application of Data Mining Techniques in Customer Relationship management: a Literature Review and Classification,” Expert Systems with Applications, vol. 36, no. 2, pp. 2592–2602, Mar. 2009, doi: https://doi.org/10.1016/j.eswa.2008.02.021.

[13] A. Wasilewski, K. Juszczyszyn, and V. Suryani, “Multi-factor evaluation of clustering methods for e-commerce application,” Egyptian Informatics Journal, vol. 28, p. 100562, Nov. 2024, doi: https://doi.org/10.1016/j.eij.2024.100562.

[14] G. Wang, “Customer segmentation in the digital marketing using a Q-learning based differential evolution algorithm integrated with K-means clustering,” PLoS ONE, vol. 20, no. 2, pp. e0318519–e0318519, Feb. 2025.

[15] P. Tzallas et al., “MAS-DR: An ML-Based Aggregation and Segmentation Framework for Residential Consumption Users to Assist DR Programs,” Sustainability, vol. 17, no. 4, p. 1551, Feb. 2025, doi: https://doi.org/10.3390/su17041551.

[16] P. J. Rousseeuw, “Silhouettes: a Graphical Aid to the Interpretation and Validation of Cluster Analysis,” Journal of Computational and Applied Mathematics, vol. 20, no. 0377–0427, pp. 53–65, Nov. 1987, doi: https://doi.org/10.1016/0377-0427(87)90125-7.

[17] L. van der Maaten and G. Hinton, "Visualizing data using t-SNE," Journal of Machine Learning Research, vol. 9, pp. 2579–2605, Nov. 2008.

[18] C. Paramasivan, D. Paul Dhinakaran, S.Stalin Panneer Selvam, S. Mukherjee, A.Pouline Juliet, and S. Rukmani Devi, “Comparing Supervised and Unsupervised Learning Technologies for Customer Segmentation in Marketing,”, 2024 Fifth International Conference on Science Technology Engineering and Mathematics (ICONSTEM), Apr. 2024, doi: https://doi.org/10.1109/iconstem60960.2024.10568702.

[19] S. Tungjitnob, K. Pasupa, and B. Suntisrivaraporn, “Identifying SME customers from click feedback on mobile banking apps: Supervised and semi-supervised approaches,” Heliyon, vol. 7, no. 8, p. e07761, Aug. 2021, doi: https://doi.org/10.1016/j.heliyon.2021.e07761.

[20] Ruchika Bhuria, S. Gupta, U. Kaur, Salil Bharany, and Pradeep Jangir, “Ensemble-based customer churn prediction in banking: a voting classifier approach for improved client retention using demographic and behavioral data,” Discover Sustainability, vol. 6, no. 1, Jan. 2025, doi: https://doi.org/10.1007/s43621-025-00807-8.

[21] Y. Qu, “Using Data Mining Techniques to Discover Customer Behavioural Patterns for Direct Marketing,” IEEE Xplore, Mar. 01, 2022. https://ieeexplore.ieee.org/document/9760309/authors#authors

[22] SAS Institute Inc. (2017), “SAS Help Center,” documentation.sas.com, Aug. 30, 2017. [Online], https://documentation.sas.com/doc/en/emref/14.3/n061bzurmej4j3n1jnj8bbjjm1a2.htm

[23] Z. Ahmad, S. Yaacob, R. Ibrahim, and W. F. Wan Fakhruddin, “The Review for Visual Analytics Methodology,” IEEE Xplore, Jun. 01, 2022. https://ieeexplore.ieee.org/abstract/document/9800100/

[24] Wiyli Yustanti, Nur Iriawan, and Irhamah Irhamah, “Categorical encoder based performance comparison in pre-processing imbalanced multiclass classification,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 31, no. 3, pp. 1705–1705, Sep. 2023, doi: https://doi.org/10.11591/ijeecs.v31.i3.pp1705-1715.

[25] Yuni Yamasari, Hani Nafisah Amaliya, R. Harimurti, Andi Iwan Nurhidayat, A. Kurniawan, and Paramitha Nerisafitra, “Classification via Clustering for Subject-based Scientific Fields in Kindergarten Students,” pp. 233–237, Oct. 2023, doi: https://doi.org/10.1109/icvee59738.2023.10348346.

[26] R Suguna, J. S. Prakash, H. A. Pai, T. R. Mahesh, V. V. Kumar, and Temesgen Engida Yimer, “Mitigating class imbalance in churn prediction with ensemble methods and SMOTE,” Scientific Reports, vol. 15, no. 1, May 2025, doi: https://doi.org/10.1038/s41598-025-01031-0.

[27] I. Made Suartana, R. E. Putra, and Yuwike Ayuningtyas, “Implementation of particle swarm optimation-support vector machine with SMOTE for stroke classification,” AIP conference proceedings, vol. 3116, pp. 060027–060027, Jan. 2024, doi: https://doi.org/10.1063/5.0210384.