The increasing complexity of therapeutic goods supply networks, characterized by multi-tier distribution systems and heterogeneous consumer behavior, necessitates robust analytical frameworks for evaluating customer revenue potential. This study investigates the application of Recency–Frequency–Monetary (RFM) analytics as a strategic tool for assessing consumer value within pharmaceutical and healthcare product supply chains. Unlike traditional valuation approaches that rely on static financial indicators, RFM analytics provides a dynamic, behavior-driven perspective, enabling firms to identify high-value customers, predict future purchasing patterns, and optimize resource allocation.

This research develops an integrated analytical framework that combines RFM metrics with clustering techniques and data mining algorithms to evaluate consumer revenue potential. Drawing upon established methodologies in customer segmentation, fuzzy clustering, and behavioral analytics, the study synthesizes theoretical and empirical insights from prior research. The framework incorporates advanced computational techniques such as ISODATA clustering and model-based segmentation to improve classification accuracy and decision-making efficiency. Furthermore, the study contextualizes these methods within therapeutic goods supply networks, where regulatory constraints, demand variability, and product criticality significantly influence purchasing behavior.

The findings demonstrate that RFM-based segmentation enhances the identification of profitable customer segments and improves forecasting accuracy compared to traditional approaches. The integration of clustering algorithms further refines segmentation granularity, enabling firms to design targeted marketing strategies and optimize inventory planning. Additionally, the study highlights the role of data-driven decision-making in improving supply chain responsiveness and financial performance.

The research contributes to both academic literature and industry practice by providing a comprehensive framework for evaluating customer value in healthcare supply networks. It addresses critical gaps in existing studies by integrating behavioral analytics with supply chain considerations, offering actionable insights for managers. The study also identifies limitations related to data availability and model assumptions, suggesting directions for future research, including the incorporation of real-time analytics and artificial intelligence.

Customer Lifetime Value, RFM Analytics, Therapeutic Supply Chain, Customer Segmentation, Behavioral Analytics, Data Mining, Clustering Algorithms, Healthcare Logistics

B.A. Abishovna, “The Principle of Effective Marketing Management ”, Procedia - Social and Behavioral Sciences, 109, pp. 1322–1325, 2014.

https://doi.org/10.1016/j.sbspro.2013.12.632

I. Bose, & X. Chen, “Detecting the migration of mobile service customers using fuzzy clustering ”, Information and Management, 52 ( 2 ), pp. 227–238, 2015. https://doi.org/10.1016/j.im.2014.11.001

C. Calvo-Porral, & J.P. Lévy-Mangin, “Profiling shopping mall customers during hard times ”, Journal of Retailing and Consumer Services, 48 ( February ), pp. 238–246, 2019. https://doi.org/10.1016/j.jretconser.2019.02.023

Y.L. Chen, M.H. Kuo, S.Y. Wu, & K. Tang, K, “Discovering recency, frequency, and monetary (RFM) sequential patterns from customers’ purchasing data ”, Electronic Commerce Research and Applications, 8 ( 5 ), pp. 241–251, 2009. https://doi.org/10.1016/j.elerap.2009.03.002

A. Di Gregorio, L. Maggioni, C. Mauri, & A. Mazzucchelli, “Employability skills for future marketing professionals ”, European Management Journal, 37 ( 3 ), pp. 251–258, 2019. https://doi.org/10.1016/j.emj.2019.03.004

He Min, Zhang Hongwei, Zhang Bo. Fuzzy ISODATA and its application in CRM[J]. Computer Applications, 2005, 25 ( 6 ): 1455–1457.

V. Holý, O. Sokol, & M. Černý, “Clustering retail products based on customer behaviour ”, Applied Soft Computing Journal, 60, pp. 752–762, 2017.

https://doi.org/10.1016/j.asoc.2017.02.004

M. Hudec, “An approach to fuzzy database querying, analysis and realisation ”, Computer Science and Information Systems, 6 ( 2 ), pp. 127–140, 2009. https://doi.org/10.2298/CSIS0902127H

S. Lian, Y. Xu, & C. Zhang, “Family profile mining in retailing ”, Decision Support Systems, 118 ( February ), pp. 102–114, 2019.

https://doi.org/10.1016/j.dss.2019.01.007

Liu Rongkai, Sun Zhonglin. PCA-KDKM algorithm and its application in weibo public opinion[J]. Journal of Shandong University of Science and Technology (Natural Science Edition), 2008, 37 ( 6 ): 1–9.

A. Mahbubi, T. Uchiyama, & K. Hatanaka, “Capturing consumer value and clustering customer p in the Indonesian halal beef market ”, Meat Science, 156 ( April ), pp. 23–32, 2019.

https://doi.org/10.1016/j.meatsci.2019.05.012

O. Motlagh, A. Berry, & L. O’Neil, “Clustering of residential electricity customers using load time series ”, Applied Energy, 237 ( December 2018 ), pp. 11–24, 2019. https://doi.org/10.1016/j.apenergy.2018.12.063

D. Vicari, & M. Alfo, “Model based clustering of customer choice data ”, Computational Statistics and Data Analysis, 71, pp. 3–13, 2014.

https://doi.org/10.1016/j.csda.2013.09.014

Xiong Lan, Gao Bing. Customer segmentation research based on RFM multi-level customer value model[J]. Business Economics Research, 2017 ( 5 ): 55–57.

Yang Bo, Huang Xiaolan. Impact of Customer Satisfaction Based on Clustering in E-commerce Factor analysis [J]. Journal of Natural Science of Xiangtan University, 2018, 40 ( 1 ): 82–85.

Ye Zhilong, Huang Zhangshu. Online member based on new 3D customer segmentation model customer value research [J]. Statistics and Information Forum, 2016, 31 ( 5 ): 96–101.

Zeng Xiaoqing, Xu Qin, Zhang Dan, et al. Multi-indicator based on consumption data mining New method of household breakdown[J]. Computer Application Research, 2013, 30 ( 10 ): 2944–2947.

Zhang Bin, Peng Qiyuan. Customer Churn Forecast Based on Railway Freight Value Classification Research [J]. Journal of Railway Science and Engineering, 2018, 15 ( 4 ): 1059–1066.

Zhang Ning, Fan Chongrui, Zhang Yan. A new collaborative filtering based on RFM model personalized recommendation algorithm [J]. Telecommunications Science, 2015, 31 ( 9 ): 110–118.

Zhao Meng, Qi Jiayin. Based on purchase behavior RFM and review behavior RFMP research on Customer Lifetime Value of Model [J]. Statistics and Information Forum, 2014, 29 ( 9 ): 91–98.

Zhao Meng, Qi Jiayin. Research on customer lifetime value based on RFM model of purchase behavior and RFMP model of comment behavior[J]. Statistics and Information Forum, 2014 ( 09 ): 91–98.