{"id":"https://openalex.org/W1999460852","doi":"https://doi.org/10.1145/1150402.1150421","title":"A general framework for accurate and fast regression by data summarization in random decision trees","display_name":"A general framework for accurate and fast regression by data summarization in random decision trees","publication_year":2006,"publication_date":"2006-08-20","ids":{"openalex":"https://openalex.org/W1999460852","doi":"https://doi.org/10.1145/1150402.1150421","mag":"1999460852"},"language":"en","primary_location":{"id":"doi:10.1145/1150402.1150421","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1150402.1150421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-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/A5100380588","display_name":"Wei Fan","orcid":"https://orcid.org/0009-0008-1900-7081"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Fan","raw_affiliation_strings":["IBM T. J. Watson Research, Hawthorne, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research, Hawthorne, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065695448","display_name":"Joe McCloskey","orcid":null},"institutions":[{"id":"https://openalex.org/I1330347796","display_name":"United States Department of Defense","ror":"https://ror.org/0447fe631","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330347796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joe McCloskey","raw_affiliation_strings":["US Department of Defense, Ft. Meade, MD"],"affiliations":[{"raw_affiliation_string":"US Department of Defense, Ft. Meade, MD","institution_ids":["https://openalex.org/I1330347796"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["IBM T. J. Watson Research, Hawthorne, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research, Hawthorne, NY","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100380588"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":1.7237,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88671324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980999827384949,"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/T10820","display_name":"Fuzzy Logic and Control Systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7211018800735474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5410706996917725},{"id":"https://openalex.org/keywords/kernel-regression","display_name":"Kernel regression","score":0.5099714994430542},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5097493529319763},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5053904056549072},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5045689344406128},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5017499923706055},{"id":"https://openalex.org/keywords/nonparametric-regression","display_name":"Nonparametric regression","score":0.45567214488983154},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45535022020339966},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43689393997192383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4166114330291748},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.41326531767845154},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.3894837200641632},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.21773439645767212},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18709784746170044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211018800735474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5410706996917725},{"id":"https://openalex.org/C200695384","wikidata":"https://www.wikidata.org/wiki/Q1739319","display_name":"Kernel regression","level":3,"score":0.5099714994430542},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5097493529319763},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5053904056549072},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5045689344406128},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5017499923706055},{"id":"https://openalex.org/C74127309","wikidata":"https://www.wikidata.org/wiki/Q3455886","display_name":"Nonparametric regression","level":3,"score":0.45567214488983154},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45535022020339966},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43689393997192383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4166114330291748},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.41326531767845154},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3894837200641632},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.21773439645767212},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18709784746170044},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1150402.1150421","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1150402.1150421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.9422","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.9422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/~wfan/PAPERS/KDD06rdt.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W128984794","https://openalex.org/W182248535","https://openalex.org/W1527119328","https://openalex.org/W1594031697","https://openalex.org/W1599871777","https://openalex.org/W1981464900","https://openalex.org/W2069888879","https://openalex.org/W2073847200","https://openalex.org/W2088912739","https://openalex.org/W2120240539","https://openalex.org/W2136185850","https://openalex.org/W2154616682","https://openalex.org/W2154925912","https://openalex.org/W2166163519","https://openalex.org/W2168106924","https://openalex.org/W2499076588","https://openalex.org/W2801490189","https://openalex.org/W2911964244","https://openalex.org/W3085162807","https://openalex.org/W4206419526","https://openalex.org/W4301861531"],"related_works":["https://openalex.org/W1541412963","https://openalex.org/W2184572292","https://openalex.org/W1509119367","https://openalex.org/W4321367829","https://openalex.org/W4309301076","https://openalex.org/W2041704562","https://openalex.org/W2288767749","https://openalex.org/W4313160815","https://openalex.org/W2181913714","https://openalex.org/W2949120947"],"abstract_inverted_index":{"Predicting":[0],"the":[1,16,38,42,60,74,81,95,107,124,144,161,177],"values":[2,83],"of":[3,9,15,27,49,62,69,110,167,185,201,212],"continuous":[4],"variable":[5],"as":[6,218,220],"a":[7,67,85,155,198,209],"function":[8],"several":[10],"independent":[11],"variables":[12],"is":[13,44,84,105,127,132,180],"one":[14],"most":[17],"important":[18],"problems":[19,64,202],"for":[20,90,134,215],"data":[21,91,111,163],"mining.":[22],"A":[23],"very":[24,128,173],"large":[25,210],"number":[26],"regression":[28,76,116,186],"methods,":[29],"both":[30],"parametric":[31,206],"and":[32,47,65,71,78,120],"nonparametric,":[33],"have":[34,99,195],"been":[35],"proposed":[36],"in":[37],"past.":[39],"However,":[40,122],"since":[41,123],"list":[43],"quite":[45,141],"extensive":[46],"many":[48,235],"these":[50,244],"models":[51],"make":[52],"rather":[53,100],"explicit,":[54],"strong":[55],"yet":[56,179],"different":[57],"assumptions":[58],"about":[59],"type":[61,184],"applicable":[63,181],"involve":[66],"lot":[68],"parameters":[70],"options,":[72],"choosing":[73],"appropriate":[75],"methodology":[77,97],"then":[79],"specifying":[80],"parameter":[82],"none-trivial,":[86],"sometimes":[87],"frustrating,":[88],"task":[89],"mining":[92,112],"practitioners.":[93],"Choosing":[94],"inappropriate":[96],"can":[98],"disappointing":[101],"results.":[102],"This":[103],"issue":[104],"against":[106],"general":[108],"utility":[109],"software.":[113],"For":[114],"example,linear":[115],"methods":[117,139,207],"are":[118,147,190,227,238],"straightforward":[119,156],"well-understood.":[121],"linear":[125],"assumption":[126],"strong,":[129],"its":[130],"performance":[131],"compromised":[133],"complicated":[135],"non-linear":[136,222],"problems.":[137,224,245],"Kernel-based":[138],"perform":[140,241],"well":[142,219,242],"if":[143],"kernel":[145],"functions":[146],"selected":[148],"correctly.":[149],"In":[150],"this":[151],"paper,":[152],"we":[153,189],"propose":[154],"approach":[157],"based":[158],"on":[159,197,243],"summarizing":[160],"training":[162],"using":[164],"an":[165],"ensemble":[166],"random":[168],"decisions":[169],"trees.":[170],"It":[171],"requires":[172],"little":[174],"knowledge":[175],"from":[176],"user,":[178],"to":[182,234,240],"every":[183],"problem":[187],"that":[188,205,237],"currently":[191],"aware":[192],"of.":[193],"We":[194],"experimented":[196],"wide":[199],"range":[200],"including":[203],"those":[204],"performwell,":[208],"selection":[211],"benchmark":[213],"datasets":[214],"nonparametric":[216],"regression,":[217],"highly":[221],"stochastic":[223],"Our":[225],"results":[226],"either":[228],"significantly":[229],"better":[230],"than":[231],"or":[232],"identical":[233],"approaches":[236],"known":[239]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}