[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125070-en":3,"doc-seo-125070-105":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},125070,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Unmasking Risky Habits - Identifying and Predicting Problem Gamblers Through Machine Learning Techniques","Machine learning techniques are widely used to identify problem gamblers, but many existing approaches depend on self-reported labels such as temporary self-exclusion or account closure. This study introduces a combined method: unsupervised labeling of problem gamblers followed by real-time prediction modeling of these users. The results provide actionable insights for designing interventions that guide or discourage disordered gambling behavior, supporting responsible gambling initiatives and healthier player habits.","Journal of Gambling Studies (2024) 40:1367–1377 [https://doi.org/10.1007/s10899-024-10297-4](https://doi.org/10.1007/s10899-024-10297-4)  \nORIGINAL PAPER  \nUnmasking Risky Habits: Identifying and Predicting Problem Gamblers Through Machine Learning Techniques  \nMáté Cs. Sándor1 · Barna Bakó1  \nAccepted: 11 February 2024 / Published online: 3 April 2024 © The Author(s) 2024  \nAbstract  \nThe use of machine learning techniques to identify problem gamblers has been widely established. However, existing methods often rely on self-reported labeling, such as temporary self-exclusion or account closure. In this study, we propose a novel approach that combines two documented methods. First we create labels for problem gamblers in an unsupervised manner. Subsequently, we develop prediction models to identify these users in real-time. The methods presented in this study offer useful insights that can be leveraged to implement interventions aimed at guiding or discouraging players from engaging in disordered gambling behaviors. This has potential implications for promoting responsible gambling and fostering healthier player habits.  \nKeywords Machine learning · Problem gambling · Identification · Prediction  \nIntroduction  \nThe gambling industry’s rapid technological transformation has led to unprecedented accessibility, contributing to a concerning rise in problem gambling cases (Potenza et al., 2011 ; Chagas & Gomes, 2017) . Although the recent pandemic initially reduced overall gambling participation, it triggered a surge in online and problem gambling, with younger individuals disproportionately affected (Wardle et al., 2021; Hodgins & Stevens, 2021) . The societal costs associated with problem gambling are projected to have a profound impact on the economy (Hofmarcher et al., 2020) . Notably, online gambling platforms employ persuasive tactics called \"sludges\" to entice users to engage in longer and riskier betting practices (Newall, 2019;Newallet al., 2020) . Moreover, the industry utilizes industrial machine learning solutions to support these practices (Coussement & De Bock, 2013), and the utilization of dark patterns has demonstrated significant effects on consumer manipulation (Bogliacino et al., 2023) . Consequently, regulatory bodies have initiated investigations into the adverse implications of online choice architecture.  \nB Barna Bakó [barna.bako@uni-corvinus.hu](barna.bako@uni-corvinus.hu)  \nMáté Cs. Sándor  \n[mate.sandor2@stud.uni-corvinus.hu](mate.sandor2@stud.uni-corvinus.hu)  \n1 Institute of Economics, Corvinus University of Budapest, Fvám tér 8, 1093 Budapest, Hungary  \nTo address the issue of problem gambling, various studies have examined the effectiveness of nudges, such as implementing loss limits and providing personalized feedback, in discouraging addictive behaviors (Brodeur, 2019;Aueretal., 2018;Auer&Griffiths, 2020) . Promising results have been observed in brick-and-mortar casino gambling through the introduction or promotion of self-and forced exclusion periods (Kotter et al., 2018) . In the case of online gambling, interventions that disrupt the gambling flow, such as fixed or self-defined monetary limits, have shown effectiveness (Folkvord et al., 2019) . However, results by Caillon et al. (2019); Giroux et al. (2017) suggest that the effectiveness of these measures in online gambling remains unclear.  \nUnsupervised machine learning techniques have been successfully used to identify vulnerable user groups in gambling (Deng et al., 2019; Braverman & Shaffer, 2012; Xuan & Shaffer, 2009) . Machine learning algorithms can also predict the development of addictive patterns (Mak et al., 2019) . Previous studies on gambling data have effectively predicted self-exclusion using supervised learning techniques like logit regression, gradient boosting, and neural networks (Percy et al., 2016; Ukhov et al., 2021; Buttigieg et al., 2022; Finkenwirth et al., 2021), relying on observed behavioral markers like frequency of play","cbCaiaLrsDBKQfA9","https://ap.wps.com/l/cbCaiaLrsDBKQfA9","pdf",401008,1,11,"English","en",105,"# Introduction\n## Interventions and limitations in online gambling\n# Methods\n## Label creation via unsupervised clustering\n## Prediction models and feature use\n# Dataset","[{\"question\":\"How does the study label problem gamblers without relying on self-reported exclusion?\",\"answer\":\"It uses unsupervised machine learning to create labels first, avoiding dependence on self-aware or self-exclusion-based labeling.\"},{\"question\":\"What modeling strategy is used to predict whether a player belongs to a problem-gambling cluster?\",\"answer\":\"After k-means clustering labels are created from a later observation window, predictive models forecast the cluster label from the player’s behavior during the initial 3-day period.\"},{\"question\":\"Why is the proposed approach considered more objective than prior supervised methods?\",\"answer\":\"By removing pre-observed labeling information and using automatic model selection (autoML) after establishing target categories, it reduces researcher bias and improves robustness across game contexts.\"}]","Unmasking Risky Habits - Identifying and Predicting Problem Gamblers Through Machine Learning Techniques | PDF",1785896464,28,{"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},"unmasking-risky-habits-identifying-and-predicting-problem-gamblers-through-machine-learning-techniques","",{"@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/unmasking-risky-habits-identifying-and-predicting-problem-gamblers-through-machine-learning-techniques/125070/",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},"How does the study label problem gamblers without relying on self-reported exclusion?","Question",{"text":75,"@type":76},"It uses unsupervised machine learning to create labels first, avoiding dependence on self-aware or self-exclusion-based labeling.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What modeling strategy is used to predict whether a player belongs to a problem-gambling cluster?",{"text":80,"@type":76},"After k-means clustering labels are created from a later observation window, predictive models forecast the cluster label from the player’s behavior during the initial 3-day period.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is the proposed approach considered more objective than prior supervised methods?",{"text":84,"@type":76},"By removing pre-observed labeling information and using automatic model selection (autoML) after establishing target categories, it reduces researcher bias and improves robustness across game contexts.","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"]