{"id":"https://openalex.org/W2899553782","doi":"https://doi.org/10.1080/03610918.2018.1563145","title":"Combining clustering of variables and feature selection using random forests","display_name":"Combining clustering of variables and feature selection using random forests","publication_year":2019,"publication_date":"2019-02-10","ids":{"openalex":"https://openalex.org/W2899553782","doi":"https://doi.org/10.1080/03610918.2018.1563145","mag":"2899553782"},"language":"en","primary_location":{"id":"doi:10.1080/03610918.2018.1563145","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2018.1563145","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Statistics - Simulation and Computation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1608.06740","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073317658","display_name":"Marie Chavent","orcid":"https://orcid.org/0000-0001-6774-597X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210166017","display_name":"Institut de Math\u00e9matiques de Bordeaux","ror":"https://ror.org/05m3r1b84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I4210141950","https://openalex.org/I4210160189","https://openalex.org/I4210166017"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210131512","display_name":"Centre de Recherche Inria Bordeaux - Sud-Ouest","ror":"https://ror.org/03tjcj052","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210131512"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marie Chavent","raw_affiliation_strings":["CQFD Team, INRIA Bordeaux Sud-Ouest, Talence, France;","Institut de Math\u00e9matiques de Bordeaux, UMR CNRS 5251, Universit\u00e9 de Bordeaux, Talence Cedex, France;","Quality control and dynamic reliability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CQFD Team, INRIA Bordeaux Sud-Ouest, Talence, France;","institution_ids":["https://openalex.org/I4210131512","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Institut de Math\u00e9matiques de Bordeaux, UMR CNRS 5251, Universit\u00e9 de Bordeaux, Talence Cedex, France;","institution_ids":["https://openalex.org/I4210166017","https://openalex.org/I15057530","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Quality control and dynamic reliability","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007400998","display_name":"Robin Genuer","orcid":"https://orcid.org/0000-0002-0981-3943"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"funder","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I4210106115","display_name":"Bordeaux Population Health","ror":"https://ror.org/00xzzba89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I15057530","https://openalex.org/I154526488","https://openalex.org/I4210106115"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210131512","display_name":"Centre de Recherche Inria Bordeaux - Sud-Ouest","ror":"https://ror.org/03tjcj052","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210131512"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Robin Genuer","raw_affiliation_strings":["ISPED, INSERM U-1219, Universit\u00e9 de Bordeaux, Bordeaux, France;","SISTM Team, INRIA Bordeaux Sud-Ouest, Talence, France","Statistics In System biology and Translational Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISPED, INSERM U-1219, Universit\u00e9 de Bordeaux, Bordeaux, France;","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I15057530","https://openalex.org/I4210106115"]},{"raw_affiliation_string":"SISTM Team, INRIA Bordeaux Sud-Ouest, Talence, France","institution_ids":["https://openalex.org/I4210131512","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Statistics In System biology and Translational Medicine","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055228462","display_name":"J\u00e9r\u00f4me Saracco","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210166017","display_name":"Institut de Math\u00e9matiques de Bordeaux","ror":"https://ror.org/05m3r1b84","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I4210141950","https://openalex.org/I4210160189","https://openalex.org/I4210166017"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210131512","display_name":"Centre de Recherche Inria Bordeaux - Sud-Ouest","ror":"https://ror.org/03tjcj052","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210131512"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J\u00e9r\u00f4me Saracco","raw_affiliation_strings":["CQFD Team, INRIA Bordeaux Sud-Ouest, Talence, France;","Institut de Math\u00e9matiques de Bordeaux, UMR CNRS 5251, Universit\u00e9 de Bordeaux, Talence Cedex, France;","Quality control and dynamic reliability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CQFD Team, INRIA Bordeaux Sud-Ouest, Talence, France;","institution_ids":["https://openalex.org/I4210131512","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Institut de Math\u00e9matiques de Bordeaux, UMR CNRS 5251, Universit\u00e9 de Bordeaux, Talence Cedex, France;","institution_ids":["https://openalex.org/I4210166017","https://openalex.org/I15057530","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Quality control and dynamic reliability","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007400998"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I154526488","https://openalex.org/I4210106115","https://openalex.org/I4210131512"],"apc_list":null,"apc_paid":null,"fwci":3.3383,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.93793209,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"50","issue":"2","first_page":"426","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9876000285148621,"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/T10320","display_name":"Neural Networks and Applications","score":0.9876000285148621,"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/T10057","display_name":"Face and Expression Recognition","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9815999865531921,"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/feature-selection","display_name":"Feature selection","score":0.8116694688796997},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7312207221984863},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7234795093536377},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7221513390541077},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6354248523712158},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5460947751998901},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.48938268423080444},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4536355137825012},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4361974895000458},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.43378469347953796},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.41382157802581787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3987692594528198},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3769576847553253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37281733751296997},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34953534603118896}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.8116694688796997},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7312207221984863},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7234795093536377},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7221513390541077},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6354248523712158},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5460947751998901},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48938268423080444},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4536355137825012},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4361974895000458},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.43378469347953796},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.41382157802581787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3987692594528198},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3769576847553253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37281733751296997},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34953534603118896}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1080/03610918.2018.1563145","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2018.1563145","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Statistics - Simulation and Computation","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1608.06740","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.06740","pdf_url":"https://arxiv.org/pdf/1608.06740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":null},{"id":"pmh:oai:HAL:hal-02013631v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02013631","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Communications in Statistics - Simulation and Computation, 2021, 50 (2), pp.426-445. &#x27E8;10.1080/03610918.2018.1563145&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/9462","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/9462","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article de revue"},{"id":"doi:10.48550/arxiv.1608.06740","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1608.06740","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1608.06740","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.06740","pdf_url":"https://arxiv.org/pdf/1608.06740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W273955616","https://openalex.org/W1493454437","https://openalex.org/W1594031697","https://openalex.org/W1853119737","https://openalex.org/W1987371344","https://openalex.org/W1992549770","https://openalex.org/W2034489756","https://openalex.org/W2047109555","https://openalex.org/W2056243712","https://openalex.org/W2085573033","https://openalex.org/W2106525823","https://openalex.org/W2107956883","https://openalex.org/W2119479037","https://openalex.org/W2122825543","https://openalex.org/W2133896831","https://openalex.org/W2135046866","https://openalex.org/W2138019504","https://openalex.org/W2155261478","https://openalex.org/W2165240856","https://openalex.org/W2170917242","https://openalex.org/W2235818404","https://openalex.org/W2557117995","https://openalex.org/W2582743722","https://openalex.org/W2782412804","https://openalex.org/W2911964244","https://openalex.org/W2951580354","https://openalex.org/W2998216295","https://openalex.org/W2998768810","https://openalex.org/W2999729612","https://openalex.org/W3099514962","https://openalex.org/W4233287056","https://openalex.org/W4285719527","https://openalex.org/W4292023222","https://openalex.org/W4298882835","https://openalex.org/W4301722118"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"Standard":[0],"approaches":[1],"to":[2,29],"tackle":[3],"high-dimensional":[4],"supervised":[5],"classification":[6],"often":[7],"include":[8],"variable":[9],"selection":[10],"and":[11,21,35,60,87],"dimension":[12],"reduction.":[13],"The":[14],"proposed":[15],"methodology":[16],"combines":[17],"clustering":[18,25,54],"of":[19,26,32,47,91,93,98],"variables":[20,27,34,48,72,94],"feature":[22],"selection.":[23],"Hierarchical":[24],"allows":[28],"built":[30],"groups":[31,46,92],"correlated":[33],"summarizes":[36],"each":[37],"group":[38],"by":[39],"a":[40,51,76],"synthetic":[41,71],"variable.":[42],"Originality":[43],"is":[44],"that":[45],"are":[49,73,83],"unknown":[50],"priori.":[52],"Moreover":[53],"approach":[55],"deals":[56],"with":[57,75],"both":[58],"numerical":[59],"categorical":[61],"variables.":[62],"Among":[63],"all":[64],"the":[65,68],"possible":[66],"partitions,":[67],"most":[69],"relevant":[70],"selected":[74],"procedure":[77],"using":[78],"random":[79],"forests.":[80],"Numerical":[81],"performances":[82],"illustrated":[84],"on":[85],"simulated":[86],"real":[88],"datasets.":[89],"Selection":[90],"provides":[95],"easier":[96],"interpretation":[97],"results.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2022-11-10T00:00:00"}
