{"id":"https://openalex.org/W2092126505","doi":"https://doi.org/10.1145/1882471.1882479","title":"Apples-to-apples in cross-validation studies","display_name":"Apples-to-apples in cross-validation studies","publication_year":2010,"publication_date":"2010-11-09","ids":{"openalex":"https://openalex.org/W2092126505","doi":"https://doi.org/10.1145/1882471.1882479","mag":"2092126505"},"language":"en","primary_location":{"id":"doi:10.1145/1882471.1882479","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882471.1882479","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","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/A5077348567","display_name":"George Forman","orcid":"https://orcid.org/0000-0003-2179-4930"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Forman","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA","Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025801122","display_name":"Martin Scholz","orcid":"https://orcid.org/0009-0005-4421-9412"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Scholz","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA","Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.5182,"has_fulltext":false,"cited_by_count":373,"citation_normalized_percentile":{"value":0.98803506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"49","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.991599977016449,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9732999801635742,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.8420215845108032},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.7713998556137085},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5850599408149719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5802923440933228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5275221467018127},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5094965100288391},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.48222267627716064},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46321991086006165},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4414982795715332},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3428024649620056},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19335895776748657},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06772968173027039}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420215845108032},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.7713998556137085},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5850599408149719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5802923440933228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5275221467018127},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5094965100288391},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.48222267627716064},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46321991086006165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4414982795715332},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3428024649620056},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19335895776748657},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06772968173027039}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1882471.1882479","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882471.1882479","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2109363337","https://openalex.org/W2133990480","https://openalex.org/W2135514714","https://openalex.org/W2150102617","https://openalex.org/W2155529673","https://openalex.org/W4235051474"],"related_works":["https://openalex.org/W4255837520","https://openalex.org/W2387011115","https://openalex.org/W4255628145","https://openalex.org/W2382043075","https://openalex.org/W2809151339","https://openalex.org/W2808854221","https://openalex.org/W2360673138","https://openalex.org/W2809370583","https://openalex.org/W2808690056","https://openalex.org/W4301447905"],"abstract_inverted_index":{"Cross-validation":[0],"is":[1,127,174],"a":[2,86,131],"mainstay":[3],"for":[4,65,106,123,138],"measuring":[5],"performance":[6,63,92,112,132],"and":[7,23,42,50,68,82,98,102,142,185],"progress":[8],"in":[9,16,30,39,62,76,143],"machine":[10,181],"learning.":[11],"There":[12],"are":[13,36,45,74,118],"subtle":[14],"differences":[15],"how":[17,107],"exactly":[18],"to":[19,55,109,164,178],"compute":[20],"accuracy,":[21],"F-measure":[22],"Area":[24],"Under":[25],"the":[26,40,58,90,100],"ROC":[27],"Curve":[28],"(AUC)":[29],"cross-validation":[31],"studies.":[32],"However,":[33],"these":[34,160],"details":[35],"not":[37],"discussed":[38],"literature,":[41],"incompatible":[43],"methods":[44,121,162],"used":[46,122],"by":[47,153],"various":[48],"papers":[49],"software":[51,183],"packages.":[52],"This":[53,94,172],"leads":[54,163],"inconsistency":[56],"across":[57],"research":[59,95],"literature.":[60],"Anomalies":[61],"calculations":[64],"particular":[66,176],"folds":[67,81],"situations":[69],"go":[70],"undiscovered":[71],"when":[72],"they":[73],"buried":[75],"aggregated":[77],"results":[78],"over":[79],"many":[80,149],"datasets,":[83],"without":[84],"ever":[85],"person":[87],"looking":[88],"at":[89],"intermediate":[91],"measurements.":[93],"note":[96],"clarifies":[97],"illustrates":[99],"differences,":[101],"it":[103],"provides":[104],"guidance":[105],"best":[108],"measure":[110,133],"classification":[111,140],"under":[113,134,168],"cross-validation.":[114],"In":[115],"particular,":[116],"there":[117],"several":[119],"divergent":[120],"computing":[124],"F-measure,":[125],"which":[126],"often":[128],"recommended":[129],"as":[130],"class":[135,170,190],"imbalance,":[136],"e.g.,":[137],"text":[139],"domains":[141],"one-vs.-all":[144],"reductions":[145],"of":[146,159,175],"datasets":[147],"having":[148],"classes.":[150],"We":[151],"show":[152],"experiment":[154],"that":[155],"all":[156],"but":[157],"one":[158],"computation":[161],"biased":[165],"measurements,":[166],"especially":[167],"high":[169,189],"imbalance.":[171,191],"paper":[173],"interest":[177],"those":[179],"designing":[180],"learning":[182],"libraries":[184],"researchers":[186],"focused":[187],"on":[188]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":49},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":40},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":10}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}