[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120362-en":3,"doc-seo-120362-105":31,"detail-sidebar-cat-0-en-105":88},{"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},120362,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Clustering Of Library’s Patron Behavior Using Machine Learning","Libraries generate abundant transaction records yet seldom use them to strengthen how patrons interact with library services. This study applies machine learning to analyze and classify patron behavior by age range, checkouts, and renewals. KMeans clustering is combined with dimensionality reduction using PCA and t-SNE to clarify underlying patterns. Model quality is supported by Calinski-Harabasz Index (320.12), Davies-Bouldin Index (0.45), and Silhouette Score (0.62), enabling data-driven service tailoring, higher satisfaction, and improved resource allocation. Results also consider data bias across library demographics.","Jurnal Teknologi Informasi & Komunikasi  \nVolume 16 Issue 1 Year 2025 | Page 1-11 | e-ISSN: 2477-3255 | ISSN: 2086-4884  \nReceived: 22-03-2024 | Revised: 12-01-2025 | Accepted: 16-02-2025  \nClustering Of Library’s Patron Behavior Using Machine Learning  \nWinda Monika1, Arbi Haza Nasution2, Febrizal Alfarasy Syam3, Chiranthi Wijesundara4  \n1Faculty of Cultural Sciences, Universitas Lancang Kuning  \n2 Faculty of Engineering, Universitas Islam Riau  \n3 Faculty of Computer Science, Universitas Lancang Kuning  \n4 University Library, University of Colombo, Sri Lanka  \n*[Corespondence: windamonika@unilak.ac.id](Corespondence: windamonika@unilak.ac.id)  \nAbstract: Libraries collect a lot of important transaction data, but they rarely use this information to improve how consumers interact with them. This work tries to bridge this gap by offering a novel use of machine learning to analyze and classify library patron behavior. The KMeans clustering technique was utilised to categorize Patron based on their age range, checkouts, and renewals. Dimensionality reduction methods like PCA and t-SNE were used to visually clarify the generated patterns. The clustering model performed quite well, as evidenced by its Calinski-Harabasz Index of 320.12, DaviesBouldin Index of 0.45, and Silhouette Score of 0.62. Beyond these metrics, the study’s novelty lies in its practical implications—offering libraries a data-driven framework to tailor services, improve user satisfaction, and optimize resource allocation. This study shows the transformative potential of machine learning in library science offering a data-driven framework for libraries to personalize services, optimize book recommendations, and enhance outreach efforts based on patron behavior. Limitation of this study lies on the data bias which may affect generalizability due to demographic differences across libraries  \nKeywords: Patron Behavior, Deep Learning, University Library, clustering  \n1. Introduction  \nThe rapid development of big data is characterized by the occurrence of a data explosion (data explosion) with diverse data characteristics (variety), very large amounts of data collected (volume), and very fast data creation (velocity) [1], [2] . The emergence of big data poses challenges for organizations to find data accurately, efficiently, and effectively extract actionable insights. On the other hand, data is a basic element or raw material for forming information which is then processed and analyzed to form knowledge. Knowledge distributed within the organization must be managed effectively to enable faster, more efficient, and more accurate decision-making. Libraries serve as hubs of information for the creation [3], storage [4], [5], management, and dissemination of knowledge [3] . Libraries collects lots of transactional data daily, including circulation records, visitation logs, bibliographic metadata, use of online databases, and so on. These transactional datasets contain meaningful and varies insights into patrons’ behavior, preferences, and usage patterns of library services. The term \"user behavior\" refers to the actions that show the preferences, proclivities, and habits that users exhibit while simultaneously utilizing and engaging with library services [4-5] . Patterns that reflect users' practices and thought processes are formed as these behaviors occur gradually over time. Some studies have found that adjustments in user behavior are being driven by advances in information technology [6], increasing information exposure [7], and societal changes such as the adoption of a new normal lifestyle following the COVID-19 pandemic [8] . Data on library visitation and book circulation during the pandemic shows that libraries had to change their offerings [9]. Thus, interpreting and  \ncomprehending user behavior is crucial for the library to provide tailored suggestions for information resources and knowledge services that are responsive to users' changing demands.  \nSeveral ","cbCairptHdm7OXOH","https://ap.wps.com/l/cbCairptHdm7OXOH","pdf",1775851,2,1,11,"English","en",105,"# Introduction\n## Big data challenges and actionable insights\n## Library transactional data and user behavior\n## Machine learning and clustering for pattern discovery","[{\"question\":\"How is clustering performance evaluated?\",\"answer\":\"Performance is assessed using Calinski-Harabasz Index (320.12), Davies-Bouldin Index (0.45), and Silhouette Score (0.62).\"},{\"question\":\"What limitations affect the study’s generalizability?\",\"answer\":\"The study notes data bias, which may limit generalizability due to demographic differences across libraries.\"}]","Clustering Of Library’s Patron Behavior Using Machine Learning | PDF",1785729670,28,{"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":83,"head_meta":85,"extra_data":87,"updated_unix":29},"clustering-of-librarys-patron-behavior-using-machine-learning","",{"@graph":37,"@context":82},[38,54,69],{"@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/clustering-of-librarys-patron-behavior-using-machine-learning/120362/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78],{"name":73,"@type":74,"acceptedAnswer":75},"How is clustering performance evaluated?","Question",{"text":76,"@type":77},"Performance is assessed using Calinski-Harabasz Index (320.12), Davies-Bouldin Index (0.45), and Silhouette Score (0.62).","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What limitations affect the study’s generalizability?",{"text":81,"@type":77},"The study notes data bias, which may limit generalizability due to demographic differences across libraries.","https://schema.org",{"og:url":52,"og:type":84,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":86,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":89},[90,94,98,102,107,112,117,120,125,128,132],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":91,"show_sort_weight":92,"slug":93},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Exam",70,"exam",{"id":103,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},5,"Comic",60,"comic",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},6,"Technology",50,"technology",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":118,"slug":119},30,"research-report",{"id":121,"doc_module":4,"doc_module_name":47,"category_name":122,"show_sort_weight":123,"slug":124},9,"Religion & Spirituality",20,"religion-spirituality",{"id":123,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":123,"slug":127},"World Cup","world-cup",{"id":129,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":129,"slug":131},10,"Lifestyle","lifestyle",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":103,"slug":135},19,"General","general"]