[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86478-en":3,"doc-seo-86478-105":30,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86478,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Data-Driven Telecom Marketing Optimization Machine Learning-Based Churn Prediction and Customer Segmentation Framework","Customer churn poses a major threat to telecom revenue and long-term relationships, while conventional retention approaches often use generic incentives and cannot precisely flag high-risk customers early. The paper proposes a complete data-driven marketing optimization framework that combines machine-learning churn prediction, two-dimensional segmentation by churn risk and customer value, and segment-specific retention/upsell actions with ROI and CLV estimation. Models (XGBoost, LightGBM, CatBoost) are tuned via stratified 5-fold cross-validation and F1-focused threshold optimization, and the deployment pipeline is built in Streamlit with SHAP explanations and automated segment reports.","Data-Driven Telecom Marketing Optimization: A Machine Learning-Based Churn Prediction and Customer Segmentation Framework  \nNada Ali, Lina Ahmed  \nDepartment of Electrical and Electronic Engineering University of Khartoum [lina.alnoosh2@gmail.com](lina.alnoosh2@gmail.com)[ ](lina.alnoosh2@gmail.com)[nadaali1232000@gmail.com](nadaali1232000@gmail.com)  \nDr. Tahani Abdalla Attia  \nAssociate Professor  \nDepartment of Electrical and Electronic Engineering University of Khartoum [tahani@uofk.edu](tahani@uofk.edu)  \narXiv :2607 . 10260v 1 [ cs .LG] 11 Jul 2026  \nAbstract—Customer churn is one of the most significant challenges facing telecommunication companies, directly eroding revenue and long-term customer relationships. Traditional retention programs typically rely on generic, non-personalized incentives and lack the precision needed to identify high-risk customers before they leave. This paper presents a complete, data-driven marketing optimization framework that integrates (i) machine-learning-based churn prediction,(ii) two-dimensional customer segmentation combining churn risk with customer value, and (iii) tailored, segment-specific marketing and Returnon-Investment (ROI) strategies. Using the IBM Telco Customer Churn dataset (7,043 customers, 21 features), three gradientboosting ensembles—XGBoost, LightGBM, and CatBoost—were trained and rigorously tuned via randomized search with stratified 5-fold cross-validation, explicit class-weighting, and F1-scoredriven decision-threshold optimization to counter the dataset’s 73.4%/26.6% class imbalance. CatBoost was selected as the deployment model, achieving 77.68% accuracy, 73.53% recall, 56.12% precision, an F1-score of 0.6366, a PR-AUC of 0.6553, anda ROC-AUC of 0.8403 on the held-out test set. Customers were subsequently partitioned with K-Means clustering (validated via the Elbow method and visualized with Principal Component Analysis) into High-, Medium-, and Low-Value segments, which were further cross-tabulated against churn-risk labels to define four actionable customer clusters. Segment-specific retention, upsell, and engagement strategies were designed for each cluster, and a theoretical ROI/CLV framework is provided to quantify the financial impact of the proposed interventions. The entire pipeline was operationalized in an interactive Streamlit web application that allows non-technical marketing teams to upload data, filter by segment, visualize churn drivers via SHAP, and download automated segment reports. The results confirm that combining predictive churn modeling with value-aware segmentation yields substantially more actionable, and more profitable, marketing decisions than churn prediction alone.  \nIndex Terms—Churn Prediction, Customer Segmentation, Gradient Boosting, XGBoost, LightGBM, CatBoost, K-Means Clustering, PCA, SHAP, Return on Investment, Customer Lifetime Value, Telecom Industry, Streamlit  \nI. INTRODUCTION  \nA. Background and Motivation  \nTelecommunication companies operate in a saturated, pricecompetitive market in which acquiring a new customer is estimated to cost several times more than retaining an existing  \none. Customer churn—the voluntary or involuntary termination of a subscriber relationship—therefore represents a direct and compounding threat to revenue. Traditional retention programs generally apply blanket incentives (discounts, bundle offers) irrespective of a customer’s actual risk of leaving or their financial value to the company, which wastes marketing budget on customers who were never going to leave while under-serving high-value customers who are quietly at risk. This paper addresses that inefficiency by building a full pipeline that predicts who is at risk, segments how valuable each customer is, and only then decides what marketing action to take and whether it pays off.  \nB. Problem Statement  \nExisting telecom retention systems suffer from three compounding weaknesses: (1) churn prediction is frequently treated as a stand-a","cbCaisVjmKG13k7t","https://ap.wps.com/l/cbCaisVjmKG13k7t","pdf",2572569,4,1,12,"English","en",105,"# Introduction\n## Background and Motivation\n## Problem Statement\n## Contributions\n## Paper Structure","[{\"question\":\"What tool supports deployment and explainability?\",\"answer\":\"An interactive Streamlit dashboard operationalizes the pipeline, enabling non-technical users to upload data, filter by segment, visualize churn drivers with SHAP, and download automated per-segment reports.\"}]",1784211996,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"data-driven-telecom-marketing-optimization-machine-learning-based-churn-prediction-and-customer-segmentation-framework","",{"@graph":36,"@context":77},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/data-driven-telecom-marketing-optimization-machine-learning-based-churn-prediction-and-customer-segmentation-framework/86478/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What tool supports deployment and explainability?","Question",{"text":75,"@type":76},"An interactive Streamlit dashboard operationalizes the pipeline, enabling non-technical users to upload data, filter by segment, visualize churn drivers with SHAP, and download automated per-segment reports.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,114,119,122,126],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":113},"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]