@article{4632,
  author = {Wei Yue},
  title = {Data Mining-Driven Customer Retention in Mobile Communication Systems},
  journal = {Journal of Intelligent Computing},
  year = {2026},
  volume = {17},
  number = {1},
  doi = {https://doi.org/10.6025/jic/2026/17/1/14-25},
  url = {https://www.dline.info/jic/fulltext/v17n1/jicv17n1_2.pdf},
  abstract = {The rapid expansion of mobile communication services and the intensification of market competition have
made customer retention a critical determinant of profitability and sustainability for telecommunications
operators. With the proliferation of operational support systems and customer interaction platforms, mobile
operators generate massive volumes of heterogeneous data that, if properly analyzed, can yield actionable
insights for strategic decision making. This paper presents a comprehensive, systematically revised study of
the application of data mining techniques to customer value analysis, segmentation, and retention in the
mobile communications sector. Building on customer lifetime value (CLV/LTV) theory and hybrid data
mining algorithms, a communication data mining model is developed to support customer relationship
management (CRM) and decision support systems. An expectation maximization (EM)-based hybrid
algorithm is employed to handle incomplete and mixed type data, enabling robust customer classification
and churn related analysis. Experimental results using SAS Enterprise Miner demonstrate satisfactory
predictive accuracy and practical relevance. The findings confirm strong associations between customer
satisfaction, loyalty, and churn risk, and highlight the importance of identifying high value yet churn prone
customer segments. This study contributes to the literature by integrating value theory, probabilistic
modeling, and data mining within the specific operational context of mobile communication enterprises,
particularly in emerging markets.},
}