{"id":{"repo_id":"corvinus","oai_identifier":"oai:phd.lib.uni-corvinus.hu:1462"},"canonical_url":"https://search.dev.ndltd.org/etd/corvinus/oai:phd.lib.uni-corvinus.hu:1462","repository":{"repo_id":"corvinus","name":"Corvinus University of Budapest","base_url":"http://phd.lib.uni-corvinus.hu/cgi/oai2"},"display":{"title":"Gambling behavior through the lens of big data","abstract":"This dissertation explores gambling behavior through a multidisciplinary, data-intensive approach that integrates behavioral economics, machine learning, and financial modeling. The research critically reassesses established behavioral models, introduces novel methodological frameworks, and provides empirical insights into gambling decision mechanisms by leveraging newly collected, publicly available datasets derived from cryptocurrency-based online gambling platforms. The work is structured into three interconnected studies. First, it challenges the well-known hot hand fallacy in gambling by replicating and critically examining previous findings, demonstrating that observed streak-dependent betting patterns can arise from methodological biases rather than true cognitive distortions. Second, it presents a machine learning framework that autonomously identifies and predicts problem gamblers without relying on self-reported labels. This approach uses unsupervised clustering to classify gambling intensity and supervised learning with automated model selection to predict problematic gambling behavior accurately across multiple time frames. Third, the research examines how Bitcoin’s price volatility and exchange rate fluctuations influence gambling behavior on the LuckyBit platform, revealing that higher Bitcoin prices increase risk-taking but reduce betting frequency, while higher volatility leads to more cautious wager sizes. Distinct behavioral responses among different gambler cohorts highlight the complex interaction of financial market dynamics and individual decision-making. Together, these studies advance the literature by providing open, reproducible, and robust data-driven tools to understand gambling behaviors in digital environments. The findings emphasize the roles of market forces, personal risk preferences, and behavioral heterogeneity, offering valuable implications for policymakers and regulators aiming to enhance responsible gambling initiatives and consumer protections in the rapidly evolving online gambling landscape.","abstract_html":"This dissertation explores gambling behavior through a multidisciplinary, data-intensive approach that integrates behavioral economics, machine learning, and financial modeling. The research critically reassesses established behavioral models, introduces novel methodological frameworks, and provides empirical insights into gambling decision mechanisms by leveraging newly collected, publicly available datasets derived from cryptocurrency-based online gambling platforms. The work is structured into three interconnected studies. First, it challenges the well-known hot hand fallacy in gambling by replicating and critically examining previous findings, demonstrating that observed streak-dependent betting patterns can arise from methodological biases rather than true cognitive distortions. Second, it presents a machine learning framework that autonomously identifies and predicts problem gamblers without relying on self-reported labels. This approach uses unsupervised clustering to classify gambling intensity and supervised learning with automated model selection to predict problematic gambling behavior accurately across multiple time frames. Third, the research examines how Bitcoin’s price volatility and exchange rate fluctuations influence gambling behavior on the LuckyBit platform, revealing that higher Bitcoin prices increase risk-taking but reduce betting frequency, while higher volatility leads to more cautious wager sizes. Distinct behavioral responses among different gambler cohorts highlight the complex interaction of financial market dynamics and individual decision-making. Together, these studies advance the literature by providing open, reproducible, and robust data-driven tools to understand gambling behaviors in digital environments. The findings emphasize the roles of market forces, personal risk preferences, and behavioral heterogeneity, offering valuable implications for policymakers and regulators aiming to enhance responsible gambling initiatives and consumer protections in the rapidly evolving online gambling landscape.","abstract_has_math":false,"creators":["Sándor, Máté Csaba"],"institution":"Budapesti Corvinus Egyetem","degree_name":"phd","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-01","date_published":"2026-01","updated_at":"2026-07-24T01:49:49Z","subjects":["Innováció, tudásgazdaság","Közgazdasági elméletek"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Sándor, Máté Csaba"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026-01-14"]},{"key":"dc:date.issued","label":"Date","values":["2026-01"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Közgazdasági és Gazdaságinformatikai Doktori Iskola"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["Budapesti Corvinus Egyetem"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://phd.lib.uni-corvinus.hu/1462/"]},{"key":"dc:type","label":"Dc Type","values":["Disszertáció"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["phd"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Innováció, tudásgazdaság","Közgazdasági elméletek"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://phd.lib.uni-corvinus.hu/1462/1/Sandor_Mate_Csaba_den.pdf","https://phd.lib.uni-corvinus.hu/1462/2/Sandor_Mate_Csaba_ten.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation explores gambling behavior through a multidisciplinary, data-intensive approach that integrates behavioral economics, machine learning, and financial modeling. The research critically reassesses established behavioral models, introduces novel methodological frameworks, and provides empirical insights into gambling decision mechanisms by leveraging newly collected, publicly available datasets derived from cryptocurrency-based online gambling platforms. The work is structured into three interconnected studies. First, it challenges the well-known hot hand fallacy in gambling by replicating and critically examining previous findings, demonstrating that observed streak-dependent betting patterns can arise from methodological biases rather than true cognitive distortions. Second, it presents a machine learning framework that autonomously identifies and predicts problem gamblers without relying on self-reported labels. This approach uses unsupervised clustering to classify gambling intensity and supervised learning with automated model selection to predict problematic gambling behavior accurately across multiple time frames. Third, the research examines how Bitcoin’s price volatility and exchange rate fluctuations influence gambling behavior on the LuckyBit platform, revealing that higher Bitcoin prices increase risk-taking but reduce betting frequency, while higher volatility leads to more cautious wager sizes. Distinct behavioral responses among different gambler cohorts highlight the complex interaction of financial market dynamics and individual decision-making. Together, these studies advance the literature by providing open, reproducible, and robust data-driven tools to understand gambling behaviors in digital environments. The findings emphasize the roles of market forces, personal risk preferences, and behavioral heterogeneity, offering valuable implications for policymakers and regulators aiming to enhance responsible gambling initiatives and consumer protections in the rapidly evolving online gambling landscape."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Gambling behavior through the lens of big data"]}]}],"canonical_facts":{"dc:creator":["Sándor, Máté Csaba"],"dc:date":["2026-01-14"],"dc:date.issued":["2026-01"],"dc:description.abstract":["This dissertation explores gambling behavior through a multidisciplinary, data-intensive approach that integrates behavioral economics, machine learning, and financial modeling. The research critically reassesses established behavioral models, introduces novel methodological frameworks, and provides empirical insights into gambling decision mechanisms by leveraging newly collected, publicly available datasets derived from cryptocurrency-based online gambling platforms. The work is structured into three interconnected studies. First, it challenges the well-known hot hand fallacy in gambling by replicating and critically examining previous findings, demonstrating that observed streak-dependent betting patterns can arise from methodological biases rather than true cognitive distortions. Second, it presents a machine learning framework that autonomously identifies and predicts problem gamblers without relying on self-reported labels. This approach uses unsupervised clustering to classify gambling intensity and supervised learning with automated model selection to predict problematic gambling behavior accurately across multiple time frames. Third, the research examines how Bitcoin’s price volatility and exchange rate fluctuations influence gambling behavior on the LuckyBit platform, revealing that higher Bitcoin prices increase risk-taking but reduce betting frequency, while higher volatility leads to more cautious wager sizes. Distinct behavioral responses among different gambler cohorts highlight the complex interaction of financial market dynamics and individual decision-making. Together, these studies advance the literature by providing open, reproducible, and robust data-driven tools to understand gambling behaviors in digital environments. The findings emphasize the roles of market forces, personal risk preferences, and behavioral heterogeneity, offering valuable implications for policymakers and regulators aiming to enhance responsible gambling initiatives and consumer protections in the rapidly evolving online gambling landscape."],"dc:format":["application/pdf"],"dc:identifier.uri":["https://phd.lib.uni-corvinus.hu/1462/1/Sandor_Mate_Csaba_den.pdf","https://phd.lib.uni-corvinus.hu/1462/2/Sandor_Mate_Csaba_ten.pdf"],"dc:language":["en"],"dc:publisher.department":["Közgazdasági és Gazdaságinformatikai Doktori Iskola"],"dc:publisher.institution":["Budapesti Corvinus Egyetem"],"dc:relation.isreferencedby":["https://phd.lib.uni-corvinus.hu/1462/"],"dc:subject":["Innováció, tudásgazdaság","Közgazdasági elméletek"],"dc:title":["Gambling behavior through the lens of big data"],"dc:type":["Disszertáció"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["phd"]},"updated_at":"2026-07-24T01:49:49Z"}