[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124571-en":3,"doc-seo-124571-105":30,"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124571,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Dynamic Customer Segmentation via Hierarchical Fragmentation-Coagulation Processes","Understanding customer behavior is essential for designing efficient marketing strategies and launching tailored programs with social value. Customer segmentation is a key task, yet dynamic modeling becomes difficult when product popularity varies, since data-scarce products can cause overfitting. This work introduces a Bayesian nonparametric model, Hierarchical Fragmentation-Coagulation Processes (HFCP), enabling shared behavior patterns across multiple products. Experiments on two real purchase datasets show automatic group-number selection, temporal split/merge tracking, cross-product pattern discovery, and improved generalization to unseen customers.","Machine Learning manuscript No.  \n(will be inserted by the editor)  \nDynamic Customer Segmentation via Hierarchical Fragmentation-Coagulation Processes  \nLing Luo* 􀀁 Bin Li 􀀁 Xuhui Fan 􀀁 Yang  \nWang 􀀁 Irena Koprinska 􀀁 Fang Chen  \nReceived: date / Accepted: date  \nAbstract Understanding customer behavior is necessary to develop efficient marketing strategies or launch tailored programs with social value for the public. Customer segmentation is a critical task for understanding diverse and dynamic customer behavior. However, as the popularity of different products varies, building dynamic customer behavior models for products with few customers may overfit the data. In this paper, we propose a new Bayesian nonparametric model for dynamic customer segmentation – Hierarchical Fragmentation-Coagulation Processes (HFCP), which allows sharing behavior patterns across multiple products. We conduct comprehensive empirical evaluations using two real-world purchase datasets. Our results show that HFCP can: (i) determine the number of groups required to model diverse customer behavior automatically; (ii) capture the changes such as split and merge of customer groups over time; (iii) discover behavior patterns shared among products and identify products with similar or different purchase behavior impacted by promotion, brand choice and change of seasons; and (iv) overcome overfitting problems and outperform previous customer segmentation models on estimating behavior for unseen customers. Hence, HFCP is a flexible and accurate segmentation model that  \nL. Luo  \nSchool of Computing and Information Systems, University of Melbourne, Melbourne, Australia Corresponding Author E-mail: [ling.luo@unimelb.edu.au](ling.luo@unimelb.edu.au)  \nB. Li  \nSchool of Computer Science, Fudan University, Shanghai, China  \nE-mail: [libin@fudan.edu.cn](libin@fudan.edu.cn)  \nX. Fan  \nSchool of Information and Physical Sciences, University of Newcastle, Australia E-mail: [xuhui.fan@newcastle.edu.au](xuhui.fan@newcastle.edu.au)  \nY. Wang and F. Chen  \nSchool of Computer Science, University of Technology Sydney, Sydney, Australia [E-mail:](E-mail: fyang.wang)[ f](E-mail: fyang.wang)[yang.wang](E-mail: fyang.wang),[fang.chen](fang.cheng@uts.edu.au)[g](fang.cheng@uts.edu.au)[@uts.edu.au](fang.cheng@uts.edu.au)  \n[I. Koprinska](I. Koprinska)  \nSchool of Computer Science, University of Sydney, Sydney, Australia E-mail: [irena.koprinska@sydney.edu.au](irena.koprinska@sydney.edu.au)  \ncan be used by stakeholders to understand dynamic customer behavior and compare the purchase behavior for different products.  \nKeywords Customer Segmentation 􀀁 Purchase Behavior Analytics 􀀁 Temporal Data Analysis 􀀁 Bayesian Temporal Models  \n1 Introduction  \nModeling customer purchase behavior is a critical task for successful business operation and marketing. Understanding customer purchase behavior allows businesses to identify the target customers that are most likely to buy their products, so that they can reach the right customers at the right time (Wang and Zhang, 2013) . An accurate purchase behavior model is necessary to develop cost-and time-efficient marketing strategies, or launch tailored programs with social value for the public. In this paper we focus on dynamic customer segmentation-identifying groups of customers with similar purchase behavior and tracking their evolution over time. Dynamic customer segmentation is a critical part in customer behavior models.  \nThe main challenges of building an accurate customer behavior model are posed by the dynamics and diversity of purchase behavior data. The customer purchase behavior can change dynamically due to various factors, such as the popularity of products, promotional campaigns and changes of seasons. For example, the availability and price of fruits such as strawberries are significantly impacted by seasonal changes, so that their sale volume fluctuates through a year. This requires a flexible temporal model to track the dynamic pu","cbCaipXpmEuzHWsi","https://ap.wps.com/l/cbCaipXpmEuzHWsi","pdf",2193326,1,32,"English","en",105,"# Introduction\n## Dynamic customer segmentation problem\n## Related approaches and modeling challenges\n## Fragmentation-Coagulation Processes (FCP) for dynamic segmentation","[{\"question\":\"What problem does the HFCP model address in customer segmentation?\",\"answer\":\"It addresses dynamic customer segmentation where customer purchase behavior changes over time and product popularity differs, which can lead to overfitting in models built for products with few customers.\"},{\"question\":\"How does HFCP model group evolution over time?\",\"answer\":\"HFCP captures temporal changes by allowing customer groups to split and merge over time, reflecting divergent or similar behavior among customer members.\"},{\"question\":\"What benefits does HFCP provide compared with prior customer segmentation models?\",\"answer\":\"HFCP can automatically determine the required number of groups, share behavior patterns across multiple products, and overcome overfitting, outperforming previous methods when estimating behavior for unseen customers.\"}]","Dynamic Customer Segmentation via Hierarchical Fragmentation-Coagulation Processes | PDF",1785893045,81,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"dynamic-customer-segmentation-via-hierarchical-fragmentation-coagulation-processes","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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":53},"https://docshare.wps.com/document/dynamic-customer-segmentation-via-hierarchical-fragmentation-coagulation-processes/124571/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the HFCP model address in customer segmentation?","Question",{"text":75,"@type":76},"It addresses dynamic customer segmentation where customer purchase behavior changes over time and product popularity differs, which can lead to overfitting in models built for products with few customers.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does HFCP model group evolution over time?",{"text":80,"@type":76},"HFCP captures temporal changes by allowing customer groups to split and merge over time, reflecting divergent or similar behavior among customer members.",{"name":82,"@type":73,"acceptedAnswer":83},"What benefits does HFCP provide compared with prior customer segmentation models?",{"text":84,"@type":76},"HFCP can automatically determine the required number of groups, share behavior patterns across multiple products, and overcome overfitting, outperforming previous methods when estimating behavior for unseen customers.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]