{"id":"https://openalex.org/W4400406244","doi":"https://doi.org/10.1007/s10994-024-06558-3","title":"A systematic approach for learning imbalanced data: enhancing zero-inflated models through boosting","display_name":"A systematic approach for learning imbalanced data: enhancing zero-inflated models through boosting","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4400406244","doi":"https://doi.org/10.1007/s10994-024-06558-3"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-024-06558-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06558-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06558-3.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06558-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080319902","display_name":"Yeasung Jeong","orcid":"https://orcid.org/0000-0002-1772-1117"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yeasung Jeong","raw_affiliation_strings":["School of Business, The State University of New York at Albany, 1400 Washington Avenue, Albany, NY, 12222, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Business, The State University of New York at Albany, 1400 Washington Avenue, Albany, NY, 12222, USA","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090574675","display_name":"Kangbok Lee","orcid":"https://orcid.org/0000-0001-9108-9554"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kangbok Lee","raw_affiliation_strings":["Harbert College of Business, Auburn University, 415 W. Magnolia Ave, Auburn, AL, 36849, USA"],"raw_orcid":"https://orcid.org/0000-0001-9108-9554","affiliations":[{"raw_affiliation_string":"Harbert College of Business, Auburn University, 415 W. Magnolia Ave, Auburn, AL, 36849, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005622939","display_name":"Young Woong Park","orcid":"https://orcid.org/0000-0003-0722-7729"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Young Woong Park","raw_affiliation_strings":["Iowa State University, 2167 Union Drive, Ames, IA, 50011, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University, 2167 Union Drive, Ames, IA, 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077276724","display_name":"Sumin Han","orcid":"https://orcid.org/0000-0003-0861-7980"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumin Han","raw_affiliation_strings":["Harbert College of Business, Auburn University, 415 W. Magnolia Ave, Auburn, AL, 36849, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbert College of Business, Auburn University, 415 W. Magnolia Ave, Auburn, AL, 36849, USA","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080319902"],"corresponding_institution_ids":["https://openalex.org/I392282"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.9864,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79362829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"113","issue":"10","first_page":"8233","last_page":"8299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.791290283203125},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.6585849523544312},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6251058578491211},{"id":"https://openalex.org/keywords/logit","display_name":"Logit","score":0.613746702671051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5797164440155029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.546771228313446},{"id":"https://openalex.org/keywords/ordered-probit","display_name":"Ordered probit","score":0.5308229327201843},{"id":"https://openalex.org/keywords/probit-model","display_name":"Probit model","score":0.5077370405197144},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48060959577560425},{"id":"https://openalex.org/keywords/probit","display_name":"Probit","score":0.4457872807979584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4177634119987488},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39326101541519165},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3922918140888214}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.791290283203125},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.6585849523544312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6251058578491211},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.613746702671051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5797164440155029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.546771228313446},{"id":"https://openalex.org/C70339092","wikidata":"https://www.wikidata.org/wiki/Q7100715","display_name":"Ordered probit","level":2,"score":0.5308229327201843},{"id":"https://openalex.org/C67257552","wikidata":"https://www.wikidata.org/wiki/Q635217","display_name":"Probit model","level":2,"score":0.5077370405197144},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48060959577560425},{"id":"https://openalex.org/C184314375","wikidata":"https://www.wikidata.org/wiki/Q3117995","display_name":"Probit","level":2,"score":0.4457872807979584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4177634119987488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39326101541519165},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3922918140888214}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-024-06558-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06558-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06558-3.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:dr.lib.iastate.edu:20.500.12876/PrMB6g0z","is_oa":false,"landing_page_url":"https://dr.lib.iastate.edu/handle/20.500.12876/PrMB6g0z","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1007/s10994-024-06558-3","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10994-024-06558-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06558-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06558-3.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400406244.pdf"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W61480698","https://openalex.org/W280536263","https://openalex.org/W837165795","https://openalex.org/W1191550839","https://openalex.org/W1250764422","https://openalex.org/W1509515766","https://openalex.org/W1526176922","https://openalex.org/W1563938718","https://openalex.org/W1567313600","https://openalex.org/W1592804209","https://openalex.org/W1607624180","https://openalex.org/W1965999333","https://openalex.org/W1974524469","https://openalex.org/W1984323748","https://openalex.org/W1986515506","https://openalex.org/W1988020501","https://openalex.org/W1990158361","https://openalex.org/W1993220166","https://openalex.org/W1996516822","https://openalex.org/W2001935432","https://openalex.org/W2004385903","https://openalex.org/W2010312834","https://openalex.org/W2012128643","https://openalex.org/W2012290523","https://openalex.org/W2026098258","https://openalex.org/W2032078163","https://openalex.org/W2053943100","https://openalex.org/W2056510602","https://openalex.org/W2059554212","https://openalex.org/W2088059023","https://openalex.org/W2089549618","https://openalex.org/W2089554791","https://openalex.org/W2091007025","https://openalex.org/W2099454382","https://openalex.org/W2103614420","https://openalex.org/W2105340608","https://openalex.org/W2107327607","https://openalex.org/W2121747822","https://openalex.org/W2123458540","https://openalex.org/W2124685890","https://openalex.org/W2126734246","https://openalex.org/W2127609382","https://openalex.org/W2133925448","https://openalex.org/W2137490863","https://openalex.org/W2146989110","https://openalex.org/W2148086182","https://openalex.org/W2148143831","https://openalex.org/W2150559772","https://openalex.org/W2157751754","https://openalex.org/W2171141701","https://openalex.org/W2285673098","https://openalex.org/W2288047259","https://openalex.org/W2338318698","https://openalex.org/W2460929823","https://openalex.org/W2620760558","https://openalex.org/W2783151797","https://openalex.org/W2794022343","https://openalex.org/W2911312162","https://openalex.org/W2912134372","https://openalex.org/W2961822132","https://openalex.org/W2965108112","https://openalex.org/W2991316847","https://openalex.org/W2994712268","https://openalex.org/W3005484410","https://openalex.org/W3013914784","https://openalex.org/W3035329113","https://openalex.org/W3035762705","https://openalex.org/W3036550407","https://openalex.org/W3113371924","https://openalex.org/W3118534316","https://openalex.org/W3121409228","https://openalex.org/W3121467893","https://openalex.org/W3160411390","https://openalex.org/W3197173171","https://openalex.org/W3210983949","https://openalex.org/W4206351417","https://openalex.org/W4210251751","https://openalex.org/W4240176047","https://openalex.org/W4243367342","https://openalex.org/W6639114710","https://openalex.org/W6676769703","https://openalex.org/W6677467840","https://openalex.org/W6850051826"],"related_works":["https://openalex.org/W3130477596","https://openalex.org/W2325840652","https://openalex.org/W2130048491","https://openalex.org/W4232966784","https://openalex.org/W1590848475","https://openalex.org/W2185638305","https://openalex.org/W3040825784","https://openalex.org/W3021446708","https://openalex.org/W2921323955","https://openalex.org/W1580427189"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"paper,":[3],"we":[4,76,86,184],"propose":[5],"systematic":[6],"approaches":[7],"for":[8,111],"learning":[9,238],"imbalanced":[10,215],"data":[11,181,212],"based":[12],"on":[13,148,175],"a":[14,45,73,78,204],"two-regime":[15,83],"process:":[16],"regime":[17,26],"0,":[18],"which":[19,28,173],"generates":[20],"excess":[21,177],"zeros":[22],"(majority":[23],"class),":[24],"and":[25,54,93,123,171,188,209,214],"1,":[27],"contributes":[29],"to":[30,139,153,236],"generating":[31],"an":[32,55],"outcome":[33],"of":[34,69,105,134,141,169,179,191,199,223],"one":[35],"(minority":[36],"class).":[37],"The":[38,143,221],"proposed":[39,193,201,229],"model":[40],"contains":[41],"two":[42],"latent":[43],"equations:":[44],"split":[46],"probit":[47,57,90],"(logit)":[48,58],"equation":[49,59],"in":[50,60,155,160],"the":[51,61,67,82,88,102,108,117,131,156,166,176,180,186,197,218,224],"first":[52],"stage":[53],"ordinary":[56],"second":[62],"stage.":[63],"Because":[64],"boosting":[65,79],"improves":[66],"accuracy":[68,234],"prediction":[70,162,233],"versus":[71],"using":[72,203],"single":[74],"classifier,":[75],"combined":[77],"strategy":[80],"with":[81],"process.":[84],"Thus,":[85],"developed":[87],"zero-inflated":[89,94],"boost":[91,96],"(ZIPBoost)":[92],"logit":[95],"(ZILBoost)":[97],"methods.":[98,194],"We":[99,128,164,195],"show":[100,129,185,226],"that":[101,130,150,227],"weight":[103,118,132],"functions":[104,119,133],"ZIPBoost":[106,170],"have":[107,136],"desired":[109],"properties":[110,138],"good":[112],"predictive":[113],"performance.":[114],"Like":[115],"AdaBoost,":[116],"upweight":[120],"misclassified":[121],"examples":[122,149],"downweight":[124],"correctly":[125],"classified":[126],"examples.":[127],"ZILBoost":[135],"similar":[137],"those":[140],"LogitBoost.":[142],"algorithm":[144],"will":[145],"focus":[146],"more":[147],"are":[151],"hard":[152],"classify":[154],"next":[157],"iteration,":[158],"resulting":[159],"improved":[161],"accuracy.":[163],"provide":[165],"relative":[167],"performance":[168,198],"ZILBoost,":[172],"rely":[174],"kurtosis":[178],"distribution.":[182],"Furthermore,":[183],"convergence":[187],"time":[189],"complexity":[190],"our":[192,200,228],"demonstrate":[196],"methods":[202,230],"Monte":[205],"Carlo":[206],"simulation,":[207],"mergers":[208],"acquisitions":[210],"(M&A)":[211],"application,":[213],"datasets":[216],"from":[217],"Keel":[219],"repository.":[220],"results":[222],"experiments":[225],"yield":[231],"better":[232],"compared":[235],"other":[237],"algorithms.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}