{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-9209"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-9209","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Fractional Random Weighted Bootstrapping for Classiﬁcation on Imbalanced Data with Ensemble Decision Tree Methods","abstract":"Ensemble methods are commonly used for building predictive models for classiﬁcation. Models that are unstable to perturbations in the training set, such as the decision tree, often see considerable reductions in error when grouped, using bootstrapped resamples of the training data to train many models. The non-parametric bootstrap, however, has limited eﬃcacy when used on severely imbalanced data, especially when the number of observations of one or more classes is exceptionally small. We explore the fractional random weighted bootstrap, which randomly assigns fractional weights to observations, as an alternative resampling pro cedure in training machine learning ensembles, particularly decision tree ensembles. We carry out a methodological study comparing the standard bagging and random forest ensemble models for decision trees against their fractionally random weighted alternatives, ﬁnding some evidence supporting their use on data with severe imbal ance.","abstract_html":"Ensemble methods are commonly used for building predictive models for classiﬁcation. Models that are unstable to perturbations in the training set, such as the decision tree, often see considerable reductions in error when grouped, using bootstrapped resamples of the training data to train many models. The non-parametric bootstrap, however, has limited eﬃcacy when used on severely imbalanced data, especially when the number of observations of one or more classes is exceptionally small. We explore the fractional random weighted bootstrap, which randomly assigns fractional weights to observations, as an alternative resampling pro cedure in training machine learning ensembles, particularly decision tree ensembles. We carry out a methodological study comparing the standard bagging and random forest ensemble models for decision trees against their fractionally random weighted alternatives, ﬁnding some evidence supporting their use on data with severe imbal ance.","abstract_has_math":false,"creators":["Carter, Sean Charles"],"institution":"University of South Florida","degree_name":"Master of Arts (M.A.)","degree_level":"Thesis","degree_discipline":"Mathematics and Statistics","degree_department":null,"school":null,"contributors":["Lu Lu, Ph.D.","Mingyang Li, Ph.D.","Seung-Yeop Lee, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-11-01T07:00:00Z","date_published":"2019-11-01T07:00:00Z","updated_at":"2026-11-19T08:51:02Z","subjects":["Bootstrapping","Classification","Decision Trees","Machine Learning","Statistics","Statistics and Probability"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/8012","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/8012","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-9209","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lu Lu, Ph.D.","Mingyang Li, Ph.D.","Seung-Yeop Lee, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Carter, Sean Charles"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-11-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mathematics and Statistics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis","M.A."]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Arts (M.A.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Bootstrapping","Classification","Decision Trees","Machine Learning","Statistics","Statistics and Probability"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/8012"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ensemble methods are commonly used for building predictive models for classiﬁcation. Models that are unstable to perturbations in the training set, such as the decision tree, often see considerable reductions in error when grouped, using bootstrapped resamples of the training data to train many models. The non-parametric bootstrap, however, has limited eﬃcacy when used on severely imbalanced data, especially when the number of observations of one or more classes is exceptionally small. We explore the fractional random weighted bootstrap, which randomly assigns fractional weights to observations, as an alternative resampling pro cedure in training machine learning ensembles, particularly decision tree ensembles. We carry out a methodological study comparing the standard bagging and random forest ensemble models for decision trees against their fractionally random weighted alternatives, ﬁnding some evidence supporting their use on data with severe imbal ance."]},{"key":"dc:title","label":"Title","values":["Fractional Random Weighted Bootstrapping for Classiﬁcation on Imbalanced Data with Ensemble Decision Tree Methods"]}]}],"canonical_facts":{"dc:contributor":["Lu Lu, Ph.D.","Mingyang Li, Ph.D.","Seung-Yeop Lee, Ph.D."],"dc:creator":["Carter, Sean Charles"],"dc:date":["2019-11-01T07:00:00Z"],"dc:description":["Ensemble methods are commonly used for building predictive models for classiﬁcation. Models that are unstable to perturbations in the training set, such as the decision tree, often see considerable reductions in error when grouped, using bootstrapped resamples of the training data to train many models. The non-parametric bootstrap, however, has limited eﬃcacy when used on severely imbalanced data, especially when the number of observations of one or more classes is exceptionally small. We explore the fractional random weighted bootstrap, which randomly assigns fractional weights to observations, as an alternative resampling pro cedure in training machine learning ensembles, particularly decision tree ensembles. We carry out a methodological study comparing the standard bagging and random forest ensemble models for decision trees against their fractionally random weighted alternatives, ﬁnding some evidence supporting their use on data with severe imbal ance."],"dc:identifier":["https://digitalcommons.usf.edu/etd/8012"],"dc:subject":["Bootstrapping","Classification","Decision Trees","Machine Learning","Statistics","Statistics and Probability"],"dc:title":["Fractional Random Weighted Bootstrapping for Classiﬁcation on Imbalanced Data with Ensemble Decision Tree Methods"],"thesis:degree_discipline":["Mathematics and Statistics"],"thesis:degree_level":["Thesis","M.A."],"thesis:degree_name":["Master of Arts (M.A.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:51:02Z"}