{"id":"https://openalex.org/W2793073217","doi":"https://doi.org/10.1109/tkde.2018.2807444","title":"CRAFTER: A Tree-Ensemble Clustering Algorithm for Static Datasets with Mixed Attributes and High Dimensionality","display_name":"CRAFTER: A Tree-Ensemble Clustering Algorithm for Static Datasets with Mixed Attributes and High Dimensionality","publication_year":2018,"publication_date":"2018-02-19","ids":{"openalex":"https://openalex.org/W2793073217","doi":"https://doi.org/10.1109/tkde.2018.2807444","mag":"2793073217"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2018.2807444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2807444","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","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/A5021436569","display_name":"Sangdi Lin","orcid":"https://orcid.org/0000-0003-2277-3701"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sangdi Lin","raw_affiliation_strings":["School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056379385","display_name":"Bahareh Azarnoush","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahareh Azarnoush","raw_affiliation_strings":["Netflix Inc., Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Netflix Inc., Los Angeles, CA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002544391","display_name":"George C. Runger","orcid":"https://orcid.org/0000-0001-9460-6983"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George C. Runger","raw_affiliation_strings":["School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021436569"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":2.4433,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91296527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"30","issue":"9","first_page":"1686","last_page":"1696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"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/T11106","display_name":"Data Management and Algorithms","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9902999997138977,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8422099351882935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7631124258041382},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.6509267687797546},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6181802749633789},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.6028260588645935},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5922654867172241},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5903759002685547},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5737665891647339},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5385704040527344},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.521446168422699},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.48271819949150085},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4631710648536682},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.4133441746234894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39160722494125366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3438228964805603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3112712502479553},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1564830243587494}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8422099351882935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631124258041382},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.6509267687797546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6181802749633789},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.6028260588645935},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5922654867172241},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5903759002685547},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5737665891647339},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5385704040527344},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.521446168422699},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.48271819949150085},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4631710648536682},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.4133441746234894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39160722494125366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3438228964805603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3112712502479553},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1564830243587494},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2018.2807444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2807444","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W273955616","https://openalex.org/W1481798977","https://openalex.org/W1498369939","https://openalex.org/W1540089290","https://openalex.org/W1563438659","https://openalex.org/W1565746575","https://openalex.org/W1672197616","https://openalex.org/W1938740620","https://openalex.org/W1972532012","https://openalex.org/W1977556410","https://openalex.org/W2006533296","https://openalex.org/W2011396747","https://openalex.org/W2021833436","https://openalex.org/W2022244837","https://openalex.org/W2033403400","https://openalex.org/W2047866469","https://openalex.org/W2083620785","https://openalex.org/W2099581008","https://openalex.org/W2103384159","https://openalex.org/W2127017215","https://openalex.org/W2132377940","https://openalex.org/W2140190241","https://openalex.org/W2141245797","https://openalex.org/W2149230623","https://openalex.org/W2157133710","https://openalex.org/W2165533158","https://openalex.org/W3003734944","https://openalex.org/W3010805239","https://openalex.org/W3120740533","https://openalex.org/W4236619680","https://openalex.org/W4244030505","https://openalex.org/W4245055982","https://openalex.org/W4246220038","https://openalex.org/W6610017368","https://openalex.org/W6628764437","https://openalex.org/W6633805893","https://openalex.org/W6636955212"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2559422900","https://openalex.org/W2590117803","https://openalex.org/W3186815950","https://openalex.org/W2393707058","https://openalex.org/W2202413591","https://openalex.org/W2389934482","https://openalex.org/W2388628913","https://openalex.org/W3124860551","https://openalex.org/W2038937869"],"abstract_inverted_index":{"Clustering":[0,112],"is":[1,40,81,107],"an":[2,114],"important":[3],"aspect":[4],"of":[5,58,64,76,94,121],"data":[6,12,87],"mining,":[7],"while":[8],"clustering":[9,29,117,124],"high-dimensional":[10],"mixed-attribute":[11],"in":[13,119],"a":[14,19,27,65,92],"scalable":[15],"fashion":[16],"still":[17],"remains":[18],"challenging":[20],"problem.":[21,38],"In":[22],"this":[23,37],"paper,":[24],"we":[25,102],"propose":[26],"tree-ensemble":[28,66],"algorithm":[30],"for":[31,89],"static":[32],"datasets,":[33,101],"CRAFTER,":[34],"to":[35,42,67,83],"tackle":[36],"CRAFTER":[39,60,106],"able":[41],"handle":[43,68],"categorical":[44],"and":[45,49,55,71,99,126],"numeric":[46],"attributes":[47,70],"simultaneously,":[48],"scales":[50],"well":[51],"with":[52],"the":[53,56,62,77,85,123,127],"dimensionality":[54],"size":[57],"datasets.":[59],"leverages":[61],"advantages":[63],"mixed":[69],"high":[72],"dimensionality.":[73],"The":[74],"concept":[75],"class":[78],"probability":[79],"estimates":[80],"utilized":[82],"identify":[84],"representative":[86],"points":[88],"clustering.":[90],"Through":[91],"series":[93],"experiments":[95],"on":[96],"both":[97,122],"synthetic":[98],"real":[100],"have":[103],"demonstrated":[104],"that":[105],"superior":[108],"than":[109],"Random":[110],"Forest":[111],"(RFC),":[113],"existing":[115],"tree-based":[116],"method,":[118],"terms":[120],"quality":[125],"computational":[128],"cost.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}