{"id":"https://openalex.org/W3008966649","doi":"https://doi.org/10.3233/ida-194477","title":"Balanced training/test set sampling for proper evaluation of classification models","display_name":"Balanced training/test set sampling for proper evaluation of classification models","publication_year":2020,"publication_date":"2020-02-18","ids":{"openalex":"https://openalex.org/W3008966649","doi":"https://doi.org/10.3233/ida-194477","mag":"3008966649"},"language":"en","primary_location":{"id":"doi:10.3233/ida-194477","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-194477","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084886882","display_name":"Donghoon Kang","orcid":"https://orcid.org/0000-0002-9774-297X"},"institutions":[{"id":"https://openalex.org/I89015989","display_name":"Dankook University","ror":"https://ror.org/058pdbn81","country_code":"KR","type":"education","lineage":["https://openalex.org/I89015989"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghoon Kang","raw_affiliation_strings":["Department of Data Science, Dankook University 152, Gyeonggi-do, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science, Dankook University 152, Gyeonggi-do, Korea","institution_ids":["https://openalex.org/I89015989"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012002123","display_name":"Sejong Oh","orcid":"https://orcid.org/0000-0002-9365-274X"},"institutions":[{"id":"https://openalex.org/I89015989","display_name":"Dankook University","ror":"https://ror.org/058pdbn81","country_code":"KR","type":"education","lineage":["https://openalex.org/I89015989"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sejong Oh","raw_affiliation_strings":["Department of Software Science, Dankook University 152, Gyeonggi-do, Korea","E-mail:","Fax: +82 41 8021 7203"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Science, Dankook University 152, Gyeonggi-do, Korea","institution_ids":["https://openalex.org/I89015989"]},{"raw_affiliation_string":"E-mail:","institution_ids":[]},{"raw_affiliation_string":"Fax: +82 41 8021 7203","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012002123"],"corresponding_institution_ids":["https://openalex.org/I89015989"],"apc_list":null,"apc_paid":null,"fwci":1.6081,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86719768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"24","issue":"1","first_page":"5","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9936000108718872,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9936000108718872,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9714999794960022,"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/T10320","display_name":"Neural Networks and Applications","score":0.9617999792098999,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7283248901367188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688840389251709},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.612398624420166},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.590724527835846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5803255438804626},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5768385529518127},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5530176162719727},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5350685119628906},{"id":"https://openalex.org/keywords/systematic-sampling","display_name":"Systematic sampling","score":0.5101971626281738},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47237780690193176},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4683878719806671},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.42865025997161865},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38234570622444153},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.35263577103614807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27044862508773804}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7283248901367188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688840389251709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.612398624420166},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.590724527835846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5803255438804626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5768385529518127},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5530176162719727},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5350685119628906},{"id":"https://openalex.org/C192489979","wikidata":"https://www.wikidata.org/wiki/Q1502997","display_name":"Systematic sampling","level":2,"score":0.5101971626281738},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47237780690193176},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4683878719806671},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42865025997161865},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38234570622444153},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35263577103614807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27044862508773804},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/ida-194477","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-194477","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1966715677","https://openalex.org/W1986453686","https://openalex.org/W1989655890","https://openalex.org/W1997429492","https://openalex.org/W1999985301","https://openalex.org/W2002009218","https://openalex.org/W2019966295","https://openalex.org/W2046653925","https://openalex.org/W2047599801","https://openalex.org/W2061387786","https://openalex.org/W2064576102","https://openalex.org/W2068972390","https://openalex.org/W2090681269","https://openalex.org/W2604200129","https://openalex.org/W3004986926"],"related_works":["https://openalex.org/W2387471420","https://openalex.org/W2381368487","https://openalex.org/W4238714840","https://openalex.org/W2078767942","https://openalex.org/W2383809451","https://openalex.org/W2548795680","https://openalex.org/W3042964584","https://openalex.org/W1438443738","https://openalex.org/W2038786780","https://openalex.org/W2181928643"],"abstract_inverted_index":{"In":[0,60,92],"machine":[1],"learning,":[2],"classification":[3,25,32,44,76,86],"involves":[4],"identifying":[5],"the":[6,31,71,85,97],"categories":[7],"or":[8],"classes":[9],"to":[10,47,125],"which":[11],"a":[12,18,24,35,43,74,112],"new":[13],"observation":[14],"belongs":[15],"based":[16],"on":[17],"training":[19,53,133,145],"set.":[20,37],"The":[21,38,137],"performance":[22,72],"of":[23,34,73,99],"model":[26,45,87],"is":[27,46],"generally":[28],"measured":[29],"by":[30],"accuracy":[33,69],"test":[36,55,68,135,147],"first":[39],"step":[40],"in":[41,90],"developing":[42],"divide":[48],"an":[49,107],"acquired":[50],"dataset":[51],"into":[52],"and":[54,102,134,146,151],"sets":[56,148],"through":[57],"random":[58,62,79,100,150],"sampling.":[59],"general,":[61],"sampling":[63,80,101,105,116,129,154],"does":[64],"not":[65],"guarantee":[66],"that":[67,127,140],"reflects":[70],"developed":[75],"model.":[77],"If":[78],"produces":[81,131,143],"biased":[82],"training/test":[83],"sets,":[84],"may":[88],"result":[89],"bias.":[91],"this":[93],"study,":[94],"we":[95],"show":[96],"problems":[98],"propose":[103,111],"balanced":[104],"as":[106],"alternative.":[108],"We":[109,118],"also":[110],"measure":[113],"for":[114],"evaluating":[115],"methods.":[117],"perform":[119],"empirical":[120],"experiments":[121],"using":[122],"benchmark":[123],"datasets":[124],"verify":[126],"our":[128,141],"algorithm":[130],"proper":[132],"sets.":[136],"results":[138],"confirm":[139],"method":[142],"better":[144],"than":[149],"several":[152],"non-random":[153],"methods":[155],"can.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}