{"id":"https://openalex.org/W4313596163","doi":"https://doi.org/10.1002/sam.11606","title":"Model selection with bootstrap validation","display_name":"Model selection with bootstrap validation","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313596163","doi":"https://doi.org/10.1002/sam.11606"},"language":"en","primary_location":{"id":"doi:10.1002/sam.11606","doi":"https://doi.org/10.1002/sam.11606","is_oa":true,"landing_page_url":"https://doi.org/10.1002/sam.11606","pdf_url":null,"source":{"id":"https://openalex.org/S40788348","display_name":"Statistical Analysis and Data Mining The ASA Data Science Journal","issn_l":"1932-1864","issn":["1932-1864","1932-1872"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-b","doyens","jufo-1","norway-1","poland-70","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Analysis and Data Mining: The ASA Data Science Journal","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1002/sam.11606","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040454660","display_name":"Rafael Savvides","orcid":"https://orcid.org/0000-0002-5796-6274","observed_orcids":["https://orcid.org/0000-0002-5796-6274"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Rafael Savvides","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0002-5796-6274","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070882636","display_name":"Jarmo M\u00e4kel\u00e4","orcid":"https://orcid.org/0000-0002-8788-3939","observed_orcids":["https://orcid.org/0000-0002-8788-3939"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jarmo M\u00e4kel\u00e4","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0002-8788-3939","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067547881","display_name":"Kai Puolam\u00e4ki","orcid":"https://orcid.org/0000-0003-1819-1047","observed_orcids":["https://orcid.org/0000-0003-1819-1047"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kai Puolam\u00e4ki","raw_affiliation_strings":["Department of Computer Science, University of Helsinki and Institute for Atmospheric and Earth System Research, University of Helsinki, Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0003-1819-1047","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki and Institute for Atmospheric and Earth System Research, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040454660"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":{"value":3760,"currency":"USD","value_usd":3760},"apc_paid":{"value":3140,"currency":"EUR","value_usd":3386},"fwci":0.4908,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.60937949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"16","issue":"2","first_page":"162","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.5601000189781189,"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":0.5601000189781189,"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/T10136","display_name":"Statistical Methods and Inference","score":0.4203999936580658,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13141","display_name":"Statistical Methods and Applications","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.9990000128746033},{"id":"https://openalex.org/keywords/bootstrap-validation","display_name":"bootstrap validation","score":0.9909999966621399},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"supervised learning","score":0.6190000176429749},{"id":"https://openalex.org/keywords/k-fold-cross-validation","display_name":"k-fold cross-validation","score":0.8840000033378601},{"id":"https://openalex.org/keywords/tolerance-parameter","display_name":"tolerance parameter","score":0.7440000176429749},{"id":"https://openalex.org/keywords/labelled-data-scarcity","display_name":"labeled data scarcity","score":0.6470000147819519},{"id":"https://openalex.org/keywords/training-data-efficiency","display_name":"training data efficiency","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618507742881775},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.6978699564933777},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.6703577637672424},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6278598308563232},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.6011132001876831},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5789346098899841},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5555887818336487},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5401408076286316},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.5065451860427856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48861581087112427},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45459723472595215},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45376861095428467},{"id":"https://openalex.org/C162040801","wikidata":"https://www.wikidata.org/wiki/Q799897","display_name":"Bootstrap aggregating","level":2,"score":0.4534556567668915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43822187185287476},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07122763991355896},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/sam.11606","doi":"https://doi.org/10.1002/sam.11606","is_oa":true,"landing_page_url":"https://doi.org/10.1002/sam.11606","pdf_url":null,"source":{"id":"https://openalex.org/S40788348","display_name":"Statistical Analysis and Data Mining The ASA Data Science Journal","issn_l":"1932-1864","issn":["1932-1864","1932-1872"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-b","doyens","jufo-1","norway-1","poland-70","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Analysis and Data Mining: The ASA Data Science Journal","raw_type":"journal-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/358454","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/358454","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["ddh","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1002/sam.11606","doi":"https://doi.org/10.1002/sam.11606","is_oa":true,"landing_page_url":"https://doi.org/10.1002/sam.11606","pdf_url":null,"source":{"id":"https://openalex.org/S40788348","display_name":"Statistical Analysis and Data Mining The ASA Data Science Journal","issn_l":"1932-1864","issn":["1932-1864","1932-1872"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-b","doyens","jufo-1","norway-1","poland-70","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Analysis and Data Mining: The ASA Data Science Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310086","display_name":"Helsingin Yliopisto","ror":"https://ror.org/040af2s02"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320322282","display_name":"Jane ja Aatos Erkon S\u00e4\u00e4ti\u00f6","ror":"https://ror.org/03vxy9y38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1517808374","https://openalex.org/W1565746575","https://openalex.org/W1585839838","https://openalex.org/W1880342431","https://openalex.org/W1978954330","https://openalex.org/W1981552604","https://openalex.org/W1982723861","https://openalex.org/W2012224392","https://openalex.org/W2081724349","https://openalex.org/W2099419573","https://openalex.org/W2127151679","https://openalex.org/W2132862423","https://openalex.org/W2154386868","https://openalex.org/W2167277498","https://openalex.org/W2582743722","https://openalex.org/W2611002985","https://openalex.org/W2765453317","https://openalex.org/W2787894218","https://openalex.org/W2897173776","https://openalex.org/W2937607577","https://openalex.org/W2949075269","https://openalex.org/W2963815651","https://openalex.org/W2979452771","https://openalex.org/W2998678080","https://openalex.org/W3026324026","https://openalex.org/W3104887532","https://openalex.org/W3106889297","https://openalex.org/W3129132077","https://openalex.org/W3149392816","https://openalex.org/W3167423243","https://openalex.org/W4232747766","https://openalex.org/W4254751698","https://openalex.org/W4283168572","https://openalex.org/W4294541781"],"related_works":["https://openalex.org/W2483623587","https://openalex.org/W2786485772","https://openalex.org/W2898280479","https://openalex.org/W7055573917","https://openalex.org/W7098203911","https://openalex.org/W3117661571","https://openalex.org/W600375314","https://openalex.org/W2782986144","https://openalex.org/W2197197475","https://openalex.org/W1996371471"],"abstract_inverted_index":{"Abstract":[0],"Model":[1],"selection":[2],"is":[3,41,45,53,61,131,136],"one":[4],"of":[5,129,156],"the":[6,17,31,34,38,80,84,91,100,147],"most":[7],"central":[8],"tasks":[9],"in":[10,108,150],"supervised":[11],"learning.":[12],"Validation":[13],"set":[14,86,120],"methods":[15,121],"are":[16,25,66],"standard":[18],"way":[19],"to":[20,55,82,89,145],"accomplish":[21],"this":[22],"task:":[23],"models":[24],"trained":[26],"on":[27,37],"training":[28],"data,":[29],"and":[30,88,110,153],"model":[32,93],"with":[33],"smallest":[35],"loss":[36],"validation":[39,51,76,85,119,134,157],"data":[40,52,65,135,141],"selected.":[42],"However,":[43],"it":[44],"generally":[46],"not":[47],"obvious":[48],"how":[49],"much":[50],"required":[54],"make":[56],"a":[57,72,95,115],"reliable":[58],"selection,":[59],"which":[60],"essential":[62],"when":[63],"labeled":[64],"scarce":[67],"or":[68,122],"expensive.":[69],"We":[70,102],"propose":[71],"bootstrap\u2010based":[73],"algorithm,":[74],"bootstrap":[75,81],"(BSV),":[77],"that":[78,104,132],"uses":[79],"adjust":[83],"size":[87],"find":[90,103],"best\u2010performing":[92],"within":[94],"tolerance":[96],"parameter":[97],"specified":[98],"by":[99],"user.":[101],"BSV":[105,130],"works":[106],"well":[107],"practice":[109],"can":[111,142],"be":[112,143],"used":[113,144],"as":[114],"drop\u2010in":[116],"replacement":[117],"for":[118],"k":[123],"\u2010fold":[124],"cross\u2010validation.":[125],"The":[126],"main":[127],"advantage":[128],"less":[133],"typically":[137],"needed,":[138],"so":[139],"more":[140],"train":[146],"model,":[148],"resulting":[149],"better":[151],"approximations":[152],"efficient":[154],"use":[155],"data.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-01-06T00:00:00"}