Industrial Innovations

Industrial Innovations

Improving subscriber retention using subscriber segmentation: Implementing the LRFM method in a mobile virtual network operator company

Document Type : Original Article

Authors
Ahmad Hakimi 1
Hossein Saadati 2
1 Department of Industrial Engineering, University of science and culture, Tehran, Iran.
2 Department of Industrial Engineering, Kharazmi University, Tehran, Iran.
10.61882/jii.3.1.84
Abstract
Customer churn is a major concern for telecommunications companies, especially in the highly competitive environment of mobile virtual network operators (MVNOs). Understanding subscriber behavior and the factors influencing churn is essential for developing effective customer retention strategies. This study investigates the behavioral patterns of mobile subscribers using LRFM (Length, Recency, Frequency, Monetary) analysis to identify key segments and churn risks. This outcome demonstrates the tangible benefits of leveraging behavioral analytics to design customer-centric retention initiatives. Unlike previous studies that often overlook MVNO-specific dynamics, this research provides actionable insights tailored to the unique operational context of MVNOs. The findings can help operators refine their promotional strategies, optimize service delivery, and ultimately build stronger, longer-lasting customer relationships in an increasingly saturated market. Our analysis reveals those subscribers with low recency scores—those who have not interacted with the service recently—are significantly more likely to churn. Based on these insights, we developed targeted re-engagement strategies and personalized service packages designed to meet the specific needs of different customer groups. These tailored offerings not only improve customer satisfaction but also help reduce churn effectively. Notably, the implementation of a focused marketing campaign led to the successful reactivation of approximately 15% of previously dormant users. Furthermore, We developed targeted re-engagement strategies and personalized service packages designed to meet the specific needs of different customer groups. These tailored offerings not only improve customer satisfaction but also help reduce churn effectively. Notably, the implementation of a focused marketing campaign led to the successful reactivation of approximately 15% of previously dormant users.
Keywords
LRFM
Segmentation method
Customer behavior analysis
Churn management
[1]    Gordini N, Veglio V. Customers churn prediction and marketing retention strategies: Application of SVM using AUC parameter selection in B2B e-commerce. Industrial Marketing Management. 2017; 62: 100–107. 
[2]    Sulikowski P, Zdziebko T. Churn factors identification in telecom. Procedia Computer Science. 2021; 192: 4800–4809.
[3]    Xu T, Ma Y, Kim K. Telecom churn prediction based on ensemble learning using feature grouping. Applied Sciences. 2021; 11(11): 4742.
[4]    Ahmad AK, Jafar A, Aljoumaa K. Customer churn prediction in telecom using machine learning in big data platform. Journal of Big Data. 2019; 6(1): 1–24. 
[5]    Tatikonda LU. The hidden costs of customer dissatisfaction. Management Accounting Quarterly. 2013; 14: 34.
[6]    Khajvand M. Estimating customer lifetime value based on RFM analysis: Case study. Procedia Computer Science. 2011; 3: 57–63. 
[7]    Zhuang Y. Customer churn prediction using improved value model and XG-Boost. Management Science and Engineering. 2018; 12(3): 51–56.
[8]    Stehani S, Karunya N, Ranjan D, Sumathipala S, Sandanayake T. Customer churn reasoning in telecom. ICIP 2020; 1–5.
[9]    Zhang Y, Qi J, Shu H, Cao J. A hybrid KNN-LR classifier for customer churn prediction. IEEE SMC. 2007; 3265–3269.
[10]    Raeisi S, Sajedi H. Customer churn prediction using gradient boosted trees. ICCKE 2020; 055–059.
[11]    Hamdi K, Zamiri A. Identifying and segmenting customers through RFM. International Business Management. 2016; 10(18): 4209–4214.
[12]    Huang B, Kechadi MT, Buckley B. Customer churn prediction in telecommunications. Expert Systems with Applications. 2012; 39(1): 1414–1425.
[13]    Saxena A, Agarwal A, Pandey BK, Pandey D. Examination of the criticality of customer segmentation using unsupervised learning methods. Circular Economy and Sustainability. 2024; 4(2): 1447–1460.
[14]    Wu S, Yau W, Ong T, Chong S. Integrated churn prediction and segmentation for telco. IEEE Access. 2021; 9: 62118–62136.
[15]    Xiahou X, Harada Y. E-commerce churn prediction based on K-means and SVM. JTAECR. 2022; 17: 458–475.
[16]    Khalili-Damghani K, Abdi F, Abolmakarem S. Hybrid soft computing approach for customer segmentation. Applied Soft Computing. 2018; 73: 816–828.
[17]    Owczarczuk M. Churn models for prepaid customers in telecom. Expert Systems with Applications. 2010; 37: 4710–4712.
[18]    Babaiyan V, Sarfarazi SA. Analyzing customers with LRFM model. Journal of AI and Data Mining. 2019; 7(2): 331–340.
[19]    Gordini N, Veglio V. Customers churn prediction and marketing retention strategies: Application of SVM using AUC parameter selection in B2B e-commerce. Industrial Marketing Management. 2017; 62: 100–107. 
[20]    Cooil B, Aksoy L, Keiningham TL. Approaches to customer segmentation. Journal of Relationship Marketing. 2008; 6(3-4): 9–39.
[21]    Schwenke C, Koller M, Wenzel S. Simulation and analysis of buying behavior in supermarkets. IEEE ETFA. 2010; 1–4. 
[22]    Griva A, Kourentzes N, Petropoulos F. Retail business analytics: Customer visit segmentation using market basket data. Expert Systems with Applications. 2018; 100: 1–16. 
[23]    Hu YH, Yeh TW. Discovering valuable frequent patterns based on RFM analysis without customer identification information. Knowledge-Based Systems. 2014; 61: 76–88. 
[24]    International Telecommunication Union. Global telecommunications report. ITU; 2021.
[25]    Joshi A, Gupta S, Joshi R. Design analysis of purchasing behavior of customers in supermarkets using TRFM model. International Journal of Innovative Research in Computer and Communication Engineering. 2016; 4(4): 7799–7806.
[26]    Morozov V, Mezentseva O, Kolomiiets A, Proskurin M. Predicting customer churn using machine learning in IT startups. Lecture Notes in Computational Intelligence and Decision Making. Springer; 2022: 645–664.
[27]    Poudel SS, Pokharel S, Timilsina M. Explaining customer churn prediction in telecom using tabular machine learning models. Machine Learning with Applications. 2024; 17: 100567.
[28]    Tauni S, Khan RI, Durrani MK, Aslam S. Impact of CRM on customer retention in telecom industry of Pakistan. Industrial Engineering Letters. 2014; 4(10): 54–59.
[29]    Xia G, He Q. Online shopping customer churn prediction based on integrated learning. MECAE 2018. Atlantis Press; 2018: 259–267.
[30]    Zhang T, Moro S, Ramos RF. A data-driven approach to improve customer churn prediction based on telecom customer segmentation. Future Internet. 2022; 14(3): 94.
[31]    Cheng CH, Chen YS. Segmenting customer value using RFM and RS theory. Expert Systems with Applications. 2009; 36(3): 6005–6011.
[32]    Jha N, Parekh D, Mouhoub M, Makkar V. Customer segmentation and churn prediction in online retail. Advances in Data Science and Management. 2020: 328–334.
[33]    Joshi A, Gupta S, Joshi R. Design analysis of purchasing behavior using TRFM model. IJIRCCE. 2016; 4(4): 7799–7806.
[34]    Khamlichi FI, Zaim D, Khalifa K. Hybrid ML model for customer churn prediction. ICDS 2019: 1–4.
[35]    Margianti ES, et al. Affinity propagation and RFM model for CRM analysis. JTAIT. 2016; 84(2): 272–282.
[36]    Murray PW, Agard B, Barajas MA. Market segmentation through data mining. Computers Industrial Engineering. 2017; 109: 233–252.
[37]    Pamina J, Raja B, SathyaBama S, Sruthi M, VJ A. Classifier for predicting churn in telecom. JARDC Systems. 2019; 11.
[38]    Rachid AD, Abdellah A, Belaid B, Rachid L. Churn prediction in e-commerce. International Journal of Electrical and Computer Engineering. 2018; 8(4): 2367.
[39]    Zadoo A, Jagtap T, Khule N, Kedari A, Khedkar S. Review on churn prediction and customer segmentation using ML. COM-IT-CON 2022; 174–178.
Industrial Innovations
Volume 3, Issue 1 - Serial Number 9
Winter 2025
Pages 84-102

  • Receive Date 27 July 2025
  • Revise Date 09 November 2025
  • Accept Date 17 November 2025