The study firstly tries to segment the value of telecommunication customers through data mining methods, and introduces variable convolution on the basis of depth-weighted K-mean algorithm for improvement. Meanwhile, grid search is introduced on the basis of extreme gradient boosting tree for optimization, and finally a telecom customer recommendation marketing model is proposed by combining the two optimization algorithms. The experiments use a publicly available dataset from Kaggle that contains telecom customer behavior data, call records, billing records, and service usage from China in 2019, totaling about 2 million pieces of information. The experimental results show that the highest value of classification accuracy of the improved depth-weighted K-mean algorithm is 95.5%, and the highest separation degree is 96.3%. In summary, the proposed model can effectively categorize telecom customers and rationally implement telecom product recommendation. The study aims to provide telecom companies with more accurate marketing decision support to improve customer satisfaction and market competitiveness.

The topic of behavioral segmentation has emerged as an important research area in e-commerce since online stores increasingly depend on customer data for personalized, recommendation, retention, pricing, and marketing decisions. Behavioral segmentation is focused on observable actions such as browsing, clicking, buying, cart interaction, channel use, response to discounts, churn, and engagement. The existing studies are split across different methods, data sets, behavioral variables, and application areas making it difficult to understand the role that behavioral segmentation plays in e-commerce. The reviewed papers presented below are a systematic review of 44 studies in e-commerce behavioral segmentation published between 2016 and 2026. The selected papers were analyzed according to the selection process, inspired by the PRISMA framework. The selected papers were reviewed along with their segments, behavioral data sources, application areas, and limitations. Behavioral segmentation techniques are dominated by RFM-based models, clustering algorithms, and machine learning. Deep learning, explainable AI, dynamic segmentation, and recommendation models are starting to dominate. Most of these studies are based on transactional data while clickstream behavior, customer journey signals, omnichannel interactions, privacy-aware modeling, and real-time segmentation are understudied. From a managerial perspective, behavioral segmentation is connected to customer retention, personalized marketing, recommendation systems, churn prediction, estimation of customer value, and strategic decision making. This review summarizes the current state of behavioral segmentation in e-commerce and outlines some directions for future research toward more dynamic, explainable, ethical, and business performance-oriented customer analytics.