{"id":"https://openalex.org/W2294175012","doi":"https://doi.org/10.1109/tpami.2016.2636831","title":"Cross-Validated Variable Selection in Tree-Based Methods Improves Predictive Performance","display_name":"Cross-Validated Variable Selection in Tree-Based Methods Improves Predictive Performance","publication_year":2016,"publication_date":"2016-12-07","ids":{"openalex":"https://openalex.org/W2294175012","doi":"https://doi.org/10.1109/tpami.2016.2636831","mag":"2294175012","pmid":"https://pubmed.ncbi.nlm.nih.gov/28114007"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2016.2636831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2016.2636831","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1512.03444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012874444","display_name":"Amichai Painsky","orcid":"https://orcid.org/0000-0002-5899-5608"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Amichai Painsky","raw_affiliation_strings":["School of Mathematical Sciences, Tel Aviv University, Ramat Aviv, Israel","School of Mathematical Sciences, Tel-Aviv University, Ramat-Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Tel Aviv University, Ramat Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"School of Mathematical Sciences, Tel-Aviv University, Ramat-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039021124","display_name":"Saharon Rosset","orcid":"https://orcid.org/0000-0002-4458-9545"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Saharon Rosset","raw_affiliation_strings":["School of Mathematical Sciences, Tel Aviv University, Ramat Aviv, Israel","School of Mathematical Sciences, Tel-Aviv University, Ramat-Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Tel Aviv University, Ramat Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"School of Mathematical Sciences, Tel-Aviv University, Ramat-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.01553599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"39","issue":"11","first_page":"2142","last_page":"2153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9876999855041504,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9807999730110168,"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/categorical-variable","display_name":"Categorical variable","score":0.8598846197128296},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7480653524398804},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6451406478881836},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6135976910591125},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5695821642875671},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5491368174552917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5454264283180237},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5417322516441345},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5355164408683777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115662217140198},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.451399028301239},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43456345796585083},{"id":"https://openalex.org/keywords/predictive-power","display_name":"Predictive power","score":0.4246743321418762},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.41066858172416687},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3841962218284607},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16861319541931152}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8598846197128296},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7480653524398804},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6451406478881836},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6135976910591125},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5695821642875671},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5491368174552917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5454264283180237},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5417322516441345},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5355164408683777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115662217140198},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.451399028301239},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43456345796585083},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.4246743321418762},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.41066858172416687},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3841962218284607},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16861319541931152},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tpami.2016.2636831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2016.2636831","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:28114007","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28114007","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1512.03444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1512.03444","pdf_url":"https://arxiv.org/pdf/1512.03444","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2294175012","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1512.03444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1512.03444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1512.03444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1512.03444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1512.03444","pdf_url":"https://arxiv.org/pdf/1512.03444","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G3085124316","display_name":null,"funder_award_id":"1487/12","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2294175012.pdf","grobid_xml":"https://content.openalex.org/works/W2294175012.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W129383413","https://openalex.org/W605537499","https://openalex.org/W1509822087","https://openalex.org/W1519043595","https://openalex.org/W1554944419","https://openalex.org/W1565746575","https://openalex.org/W1678356000","https://openalex.org/W1875061881","https://openalex.org/W1967610656","https://openalex.org/W1981552604","https://openalex.org/W1985995090","https://openalex.org/W2026824186","https://openalex.org/W2072154218","https://openalex.org/W2123998733","https://openalex.org/W2125055259","https://openalex.org/W2129018774","https://openalex.org/W2143684265","https://openalex.org/W2153476503","https://openalex.org/W2154415584","https://openalex.org/W2161349318","https://openalex.org/W2170179227","https://openalex.org/W2911964244","https://openalex.org/W4249991467","https://openalex.org/W6603851545","https://openalex.org/W6605243846","https://openalex.org/W6618413705","https://openalex.org/W6630591262","https://openalex.org/W6630956611","https://openalex.org/W6637386731","https://openalex.org/W6682981795","https://openalex.org/W6684950362"],"related_works":["https://openalex.org/W1669748612","https://openalex.org/W2974190803","https://openalex.org/W2786970068","https://openalex.org/W2038030840","https://openalex.org/W1512426554","https://openalex.org/W3095004521","https://openalex.org/W1979279626","https://openalex.org/W1599871777","https://openalex.org/W2949377985","https://openalex.org/W2181164912","https://openalex.org/W2019978710","https://openalex.org/W3049515436","https://openalex.org/W2522733224","https://openalex.org/W1764975672","https://openalex.org/W1509515766","https://openalex.org/W1999460852","https://openalex.org/W2914135034","https://openalex.org/W2277386071","https://openalex.org/W2117308311","https://openalex.org/W98929787"],"abstract_inverted_index":{"Recursive":[0],"partitioning":[1,20],"methods":[2,29,155],"producing":[3],"tree-like":[4],"models":[5,152],"are":[6,59,122],"a":[7,15,53,70,87],"long":[8],"standing":[9],"staple":[10],"of":[11,24,36,56,65,104,148],"predictive":[12,129],"modeling.":[13],"However,":[14],"fundamental":[16],"flaw":[17],"in":[18,43,61,118,133],"the":[19,62,82,97,146,177],"(or":[21],"splitting)":[22],"rule":[23],"commonly":[25],"used":[26,117],"tree":[27,119,151],"building":[28,120],"precludes":[30],"them":[31],"from":[32],"treating":[33],"different":[34],"types":[35],"variables":[37,51,110],"equally.":[38],"This":[39],"most":[40,101],"clearly":[41],"manifests":[42],"these":[44],"methods'":[45],"inability":[46],"to":[47,72,128,182],"properly":[48],"utilize":[49,157],"categorical":[50,109],"with":[52,111],"large":[54],"number":[55],"categories,":[57],"which":[58,169],"ubiquitous":[60],"new":[63],"age":[64],"big":[66],"data.":[67],"We":[68,131],"propose":[69],"framework":[71],"splitting":[73,83,142,166],"using":[74],"leave-one-out":[75],"(LOO)":[76],"cross":[77],"validation":[78],"(CV)":[79],"for":[80,96,164,184],"selecting":[81],"variable,":[84],"then":[85],"performing":[86],"regular":[88],"split":[89],"(in":[90],"our":[91,105,141],"case,":[92],"following":[93],"CART's":[94],"approach)":[95],"selected":[98],"variable.":[99],"The":[100],"important":[102],"consequence":[103],"approach":[106,143],"is":[107],"that":[108,140,156],"many":[112],"categories":[113],"can":[114],"be":[115],"safely":[116],"and":[121,136,153],"only":[123],"chosen":[124],"if":[125],"they":[126],"contribute":[127],"power.":[130],"demonstrate":[132],"extensive":[134],"simulation":[135],"real":[137],"data":[138],"analysis":[139],"significantly":[144],"improves":[145],"performance":[147],"both":[149],"single":[150],"ensemble":[154],"trees.":[158],"Importantly,":[159],"we":[160],"design":[161],"an":[162],"algorithm":[163],"LOO":[165],"variable":[167],"selection":[168],"under":[170],"reasonable":[171],"assumptions":[172],"does":[173],"not":[174],"substantially":[175],"increase":[176],"overall":[178],"computational":[179],"complexity":[180],"compared":[181],"CART":[183],"two-class":[185],"classification.":[186]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}