Predicting human behavior presents significant challenges in various domains. Chapter 1 adopts a novel methodological approach, utilizing neurophysiological responses measured and utilized machine learning to predict hit songs. Statistical analyses reveal the effectiveness of machine learning techniques, showcasing a 97% accuracy in classifying hit songs. This underscores the potential of machine learning applied to neural data in enhancing market outcome predictions. Chapter 2 focuses on the proactive assessment of mood among the elderly using continuous neurophysiological data. By integrating self-reports with neurophysiological measures, the study demonstrates a high predictive accuracy in identifying low mood and energy levels. Applications of such predictions can enable timely interventions to mitigate the risk of depression in vulnerable populations. In Chapter 3, a proactive approach to mental health assessment is explored through the continuous collection of neurophysiological data in the same population as chapter 2. Statistical analyses unveil the predictive power of neurophysiological troughs and peaks in determining daily mood fluctuations, with machine learning models achieving 90% accuracy. The study underscores the viability of commercially available neuroscientific technologies in assessing mood disorders and promoting well-being. Collectively, this dissertation underscores the transformative potential of neuroscientific methodologies in predicting human behavior and experience. By leveraging machine learning and continuous neurophysiological monitoring, these studies offer insights into proactive interventions and personalized approaches to improve societal well-being and prevent mental health crises.
","abstract_html":"<p>Predicting human behavior presents significant challenges in various domains. Chapter 1 adopts a novel methodological approach, utilizing neurophysiological responses measured and utilized machine learning to predict hit songs. Statistical analyses reveal the effectiveness of machine learning techniques, showcasing a 97% accuracy in classifying hit songs. This underscores the potential of machine learning applied to neural data in enhancing market outcome predictions. Chapter 2 focuses on the proactive assessment of mood among the elderly using continuous neurophysiological data. By integrating self-reports with neurophysiological measures, the study demonstrates a high predictive accuracy in identifying low mood and energy levels. Applications of such predictions can enable timely interventions to mitigate the risk of depression in vulnerable populations. In Chapter 3, a proactive approach to mental health assessment is explored through the continuous collection of neurophysiological data in the same population as chapter 2. Statistical analyses unveil the predictive power of neurophysiological troughs and peaks in determining daily mood fluctuations, with machine learning models achieving 90% accuracy. The study underscores the viability of commercially available neuroscientific technologies in assessing mood disorders and promoting well-being. Collectively, this dissertation underscores the transformative potential of neuroscientific methodologies in predicting human behavior and experience. By leveraging machine learning and continuous neurophysiological monitoring, these studies offer insights into proactive interventions and personalized approaches to improve societal well-being and prevent mental health crises.</p>","abstract_has_math":false,"creators":["Merritt, Sean Hyrum"],"institution":null,"degree_name":"Economics, PhD","degree_level":"Restricted to Claremont Colleges Dissertation","degree_discipline":"School of Social Science, Politics, and Evaluation","degree_department":null,"school":null,"contributors":["Greg DeAngelo","Monic Capra"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-01-01T08:00:00Z","date_published":"2024-01-01T08:00:00Z","updated_at":"2026-07-24T01:41:01Z","subjects":["Human behavior","Neurophysiological data","Machine learning","Statistical analyses","Mood disorders","Economics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarship.claremont.edu/cgu_etd/793","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Greg DeAngelo","Monic Capra"]},{"key":"dc:creator","label":"Author","values":["Merritt, Sean Hyrum"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2024-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["School of Social Science, Politics, and Evaluation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Restricted to Claremont Colleges Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Economics, PhD"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Human behavior","Neurophysiological data","Machine learning","Statistical analyses","Mood disorders","Economics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarship.claremont.edu/cgu_etd/793"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Predicting human behavior presents significant challenges in various domains. Chapter 1 adopts a novel methodological approach, utilizing neurophysiological responses measured and utilized machine learning to predict hit songs. Statistical analyses reveal the effectiveness of machine learning techniques, showcasing a 97% accuracy in classifying hit songs. This underscores the potential of machine learning applied to neural data in enhancing market outcome predictions. Chapter 2 focuses on the proactive assessment of mood among the elderly using continuous neurophysiological data. By integrating self-reports with neurophysiological measures, the study demonstrates a high predictive accuracy in identifying low mood and energy levels. Applications of such predictions can enable timely interventions to mitigate the risk of depression in vulnerable populations. In Chapter 3, a proactive approach to mental health assessment is explored through the continuous collection of neurophysiological data in the same population as chapter 2. Statistical analyses unveil the predictive power of neurophysiological troughs and peaks in determining daily mood fluctuations, with machine learning models achieving 90% accuracy. The study underscores the viability of commercially available neuroscientific technologies in assessing mood disorders and promoting well-being. Collectively, this dissertation underscores the transformative potential of neuroscientific methodologies in predicting human behavior and experience. By leveraging machine learning and continuous neurophysiological monitoring, these studies offer insights into proactive interventions and personalized approaches to improve societal well-being and prevent mental health crises.
"]},{"key":"dc:title","label":"Title","values":["Applying Machine Learning and Neurophysiology to Improve Accuracy of Predicting Human Behavior"]}]}],"canonical_facts":{"dc:contributor":["Greg DeAngelo","Monic Capra"],"dc:creator":["Merritt, Sean Hyrum"],"dc:date.available":["2024-06-01T07:00:00Z"],"dc:description.abstract":["Predicting human behavior presents significant challenges in various domains. Chapter 1 adopts a novel methodological approach, utilizing neurophysiological responses measured and utilized machine learning to predict hit songs. Statistical analyses reveal the effectiveness of machine learning techniques, showcasing a 97% accuracy in classifying hit songs. This underscores the potential of machine learning applied to neural data in enhancing market outcome predictions. Chapter 2 focuses on the proactive assessment of mood among the elderly using continuous neurophysiological data. By integrating self-reports with neurophysiological measures, the study demonstrates a high predictive accuracy in identifying low mood and energy levels. Applications of such predictions can enable timely interventions to mitigate the risk of depression in vulnerable populations. In Chapter 3, a proactive approach to mental health assessment is explored through the continuous collection of neurophysiological data in the same population as chapter 2. Statistical analyses unveil the predictive power of neurophysiological troughs and peaks in determining daily mood fluctuations, with machine learning models achieving 90% accuracy. The study underscores the viability of commercially available neuroscientific technologies in assessing mood disorders and promoting well-being. Collectively, this dissertation underscores the transformative potential of neuroscientific methodologies in predicting human behavior and experience. By leveraging machine learning and continuous neurophysiological monitoring, these studies offer insights into proactive interventions and personalized approaches to improve societal well-being and prevent mental health crises.
"],"dc:identifier":["https://scholarship.claremont.edu/cgu_etd/793"],"dc:subject":["Human behavior","Neurophysiological data","Machine learning","Statistical analyses","Mood disorders","Economics"],"dc:title":["Applying Machine Learning and Neurophysiology to Improve Accuracy of Predicting Human Behavior"],"thesis:degree_discipline":["School of Social Science, Politics, and Evaluation"],"thesis:degree_level":["Restricted to Claremont Colleges Dissertation"],"thesis:degree_name":["Economics, PhD"]},"updated_at":"2026-07-24T01:41:01Z"}