Application of HDBSCAN Algorithm for WhatsApp Lead Segmentation in Sales Strategy Optimization in CV. Multi Engineering Partners
DOI:
https://doi.org/10.37476/presed.v3i1.131Keywords:
HDBSCAN, Leads, WhatsApp, Clustering, CRMAbstract
The development of the use of WhatsApp as the main communication channel in the pre-sales process for SMEs produces large, complex, and heterogeneous lead data, thus requiring an analytical approach to improve the effectiveness of lead management. This study applied the HDBSCAN (Hierarchical Density-Based Spatial Clustering of Applications with Noise) algorithm to segment WhatsApp leads on CVs. Multi Engineering Partners used observation-based simulated datasets for the January-June 2025 period. The research follows the CRISP-DM framework through the stages of business understanding, data preparation, modeling, evaluation, and deployment. The main variables analyzed included the number of chats, average response time, frequency of follow-ups, source of leads, and closing status. The results of the analysis showed that HDBSCAN was able to form multiple clusters automatically without determining the number of clusters at the beginning, while detecting noise that represented passive or non-potential leads. Clusters with high communication intensity show a greater closure rate so that they can be prioritized for follow-up strategies. These findings confirm that HDBSCAN is effective in handling data leads with varied characteristics and can be a solution for SMEs in optimizing data-driven sales strategies. This research contributes in the form of a Business Intelligence pipeline to support decision-making and recommendations to improve sales performance.
References
Auliani, S. N. (2024). Implementation of Density-Based Spatial Clustering of Applications with Noise and Fuzzy C – Means for Clustering Car Sales. The Indonesian Journal of Computer Science, 13(4). https://doi.org/10.33022/ijcs.v13i4.4135
Blachowicz, T., Wylezek, J., Sokol, Z., & Bondel, M. (2025). Real-Time Analysis of Industrial Data Using the Unsupervised Hierarchical Density-Based Spatial Clustering of Applications with Noise Method in Monitoring the Welding Process in a Robotic Cell. Information (Switzerland), 16(2). https://doi.org/10.3390/info16020079
Chitra, J., & Heikal, J. (2024). Customer segmentation using the K-Means Clustering algorithm in Foreign Banks in Indonesia. In Indonesia Accounting Research Journal (Vol. 11, Issue 4).
Dwi Handayani, F., & Rosyida, I. (2023). Clustering Review Pengguna Aplikasi Zenius pada Layanan Google Play Store Menggunakan Metode DBSCAN dan HDBSCAN. Emerging Statistics and Data Science Journal, 1(2).
González-Alemán, R., Platero-Rochart, D., Rodríguez-Serradet, A., Hernández-Rodríguez, E. W., Caballero, J., Leclerc, F., & Montero-Cabrera, L. (2022). MDSCAN: RMSD-based HDBSCAN clustering of long molecular dynamics. Bioinformatics, 38(23), 5191–5198. https://doi.org/10.1093/bioinformatics/btac666
Handijono, A., Irawan Gunarto, R., & Sutrisna, E. (2024). Memanfaatkan Whatsapps Business untuk Promosi dan Penjualan. 4(1). https://doi.org/10.37481
Hidayat, A. I., & Wahdanial Asbara, N. (2024). Utilization of IoT Technology to Optimize Business Processes in Oyster Mushroom Houses. Proceeding of Research and Civil Society Desemination, 2(1), 387–390. https://doi.org/10.37476/presed.v2i1.82
Hidayat, M., Latief, F., Widiawati, A., Asbara, N. W., & Zaeni, N. (2021). Factors Supporting Business and its Distrubution to Business Resilience In New Normal Era. Journal of Distribution Science, 19(11), 5–15. https://doi.org/10.15722/jds.19.11.202111.5
Nhat, N. M. (2024). Applied Density-Based Clustering Techniques for Classifying High-Risk Customers: A Case Study of Commercial Banks in Vietnam. Journal of Applied Data Sciences, 5(4), 1639–1653. https://doi.org/10.47738/jads.v5i4.344
Nisak, C., & Sugiharti, E. (2024). Customer Lifetime Value Clustering Using K-Means Algorithm with Length Recency Frequency Monetary Model to Enhance Customer Relationship Management ARTICLE HISTORY. Journal of Advances in Information Systems and Technology, 6(1).
Stewart, G., & Al-Khassaweneh, M. (2022). An Implementation of the HDBSCAN* Clustering Algorithm. Applied Sciences (Switzerland), 12(5). https://doi.org/10.3390/app12052405
Yudiana, Y., Yulia Agustina, A., & Nur Khofifah, dan. (2023). Prediksi Customer Churn Menggunakan Metode CRISP-DM Pada Industri Telekomunikasi Sebagai Implementasi Mempertahankan Pelanggan (Vol. 8, Issue 1). https://doi.org/doi.org/10.30631/ijoieb.v8i1.1710
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Proceeding of Research and Civil Society Desemination
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
