[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125474-en":3,"doc-seo-125474-105":31,"detail-sidebar-cat-0-en-105":91},{"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":28,"seo_description":14,"update_tm":29,"read_time":30},125474,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Building a new hybrid machine learning model for improvement insurance cross-sell prediction","Amid rising competition in the insurance sector, optimizing cross-selling strategies is crucial for sustainable growth and requires a deep understanding of customer behavior. This study proposes a machine learning-driven framework for cross-sell prediction to enhance personalization, increase conversion rates, and maximize return on investment. Using 381,109 customer records, the data are preprocessed via outlier treatment, categorical encoding, and feature standardization. Borderline-SMOTE addresses class imbalance, and four models are evaluated. XGBoost with Borderline-SMOTE yields the best performance (accuracy 0.84; ROC-AUC 0.8436), improving over a baseline, and visual analysis reveals actionable behavioral patterns.","Building a new hybrid machine learning model for improvement insurance cross-sell prediction  \nNgoc Gia Bao Doan 1,2, Quan Minh Luu 1,2, Ha Thi Thanh Truong 1,2, Tan Duc Minh Nguyen 1,2, Huyen Thi Minh Phan 1,2, Duy Thanh Tran1,2* 1University of Economics and Law, Ho Chi Minh City, Vietnam 2Vietnam National University, Ho Chi Minh City, Vietnam  \n*Corresponding author: [thanhtd@uel.edu.vn](thanhtd@uel.edu.vn)  \n\n| ARTICLE INFO |  | ABSTRACT |\n| --- | --- | --- |\n| DOI:10 .46223/HCMCOUJS. econ.en.16.1.4306.2026\u003Cbr>Received: April 13th, 2025\u003Cbr>Revised: May 06th, 2025\u003Cbr>Accepted: June 02nd, 2025\u003Cbr>JEL classification code: C53; E27; E37\u003Cbr>Keywords:\u003Cbr>Borderline-SMOTE; crosssell prediction; decision tree; hybrid model; logistic regression; random forest; ROC-AUC; XGBoost | Amid rising competition in the insurance sector, optimizing cross-selling strategies is crucial for sustainable growth and requires a deep understanding of customer behavior. This study proposes a machine learning-driven framework for cross-sell prediction to enhance personalization, increase conversion rates, and maximize return on investment. Using 381,109 customer records from an insurance company, the data undergoes preprocessing steps including outlier treatment for Annual Premium, encoding categorical variables such as Gender and Vehicle Age, and standardizing numerical features like Age, Annual Premium, and Vintage. To address class imbalance in the Response variable, where only 12.26 percent of customers responded positively, Borderline-Synthetic Minority Oversampling Technique (Borderline-SMOTE) is applied to generate synthetic samples and improve prediction accuracy. Four machine learning models, including Logistic Regression, Decision Tree, Random Forest, and XGBoost, are trained and evaluated using Accuracy, Receiver Operating Characteristic-Area Under the Curve (ROC-AUC), Mean Absolute Error, Mean Squared Error, and Root Mean Squared Error. Among these, XGBoost with BorderlineSMOTE achieves the best performance, with an accuracy of 0.84 anda ROC-AUC score of 0.8436, representing a significant improvement over the baseline XGBoost model with a ROC-AUC of 0.7768. Logistic Regression also improves, with its ROC-AUC increasing from 0.8250 to 0.8451. Visual analysis reveals behavioral patterns, such as a 25 percent purchase rate among customers with vehicles older than two years and a 20 percent rate among male customers with prior vehicle damage. The study delivers a high-performing predictive model to support targeted marketing efforts, potentially increasing cross-sell conversion rates by 5 to 10 percent. Future work will explore deep learning techniques and larger datasets to further enhance prediction capabilities |  |\n\n1. Introduction  \nIn today’s competitive market, understanding customer behavior and optimizing sales strategies are crucial for business growth. Cross-sell prediction, which involves recommending complementary products to existing customers, is a key method to enhance revenue and customer lifetime value. By utilizing data analytics, businesses can personalize recommendations and improve profitability. However, accurately predicting cross-sell  \nopportunities remains a significant challenge due to the multidimensional nature of consumer behavior, evolving purchasing patterns, and unpredictable market fluctuations.  \nSeveral studies have explored cross-sell prediction using different approaches, yet limitations persist. For instance, Mixed Data Factor Analysis was employed in the banking sector but struggled to integrate transaction data with survey insights (Kamakura et al., 2003) . In the insurance industry, a machine learning based system was proposed to support crossselling, but it faced several limitations, such as insufficient parameter tuning and poor handling of class imbalance (Tian et al., 2023) . Similarly, Explainable AI (XAI) was utilized to enhance model interpretability in energy retail, though it lacked an in-depth","cbCaitPaCSHbOZIM","https://ap.wps.com/l/cbCaitPaCSHbOZIM","pdf",771752,2,1,19,"English","en",105,"# Introduction\n# Related research","[{\"question\":\"What problem does this study address in insurance cross-selling?\",\"answer\":\"It targets the challenge of accurately predicting cross-sell opportunities from multidimensional and evolving customer behavior, to improve personalization and business profitability.\"},{\"question\":\"How does the study handle class imbalance in the response variable?\",\"answer\":\"It applies Borderline-SMOTE to generate synthetic samples for the minority positive class, improving prediction accuracy despite conversions being a small fraction.\"},{\"question\":\"Which model combination performs best and how is it evaluated?\",\"answer\":\"XGBoost with Borderline-SMOTE performs best, evaluated using metrics including Accuracy, ROC-AUC, MAE, MSE, and RMSE.\"}]","Building a new hybrid machine learning model for improvement insurance cross-sell prediction | PDF",1785899201,48,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":29},"building-a-new-hybrid-hybrid-machine-learning-model-for-improvement-insurance-cross-sell-prediction","",{"@graph":37,"@context":85},[38,54,68],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/building-a-new-hybrid-hybrid-machine-learning-model-for-improvement-insurance-cross-sell-prediction/125474/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does this study address in insurance cross-selling?","Question",{"text":75,"@type":76},"It targets the challenge of accurately predicting cross-sell opportunities from multidimensional and evolving customer behavior, to improve personalization and business profitability.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study handle class imbalance in the response variable?",{"text":80,"@type":76},"It applies Borderline-SMOTE to generate synthetic samples for the minority positive class, improving prediction accuracy despite conversions being a small fraction.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model combination performs best and how is it evaluated?",{"text":84,"@type":76},"XGBoost with Borderline-SMOTE performs best, evaluated using metrics including Accuracy, ROC-AUC, MAE, MSE, and RMSE.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":47,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]