{"id":"https://openalex.org/W2085005783","doi":"https://doi.org/10.1145/1871437.1871758","title":"BagBoo","display_name":"BagBoo","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2085005783","doi":"https://doi.org/10.1145/1871437.1871758","mag":"2085005783"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871758","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","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/A5110057155","display_name":"Dmitry Pavlov","orcid":null},"institutions":[{"id":"https://openalex.org/I58957048","display_name":"Yandex (Russia)","ror":"https://ror.org/04dbch786","country_code":"RU","type":"company","lineage":["https://openalex.org/I58957048"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Dmitry Yurievich Pavlov","raw_affiliation_strings":["Yandex, Palo Alto, CA, USA","Yandex, Palo Alto, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yandex, Palo Alto, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Yandex, Palo Alto, CA, USA#TAB#","institution_ids":["https://openalex.org/I58957048"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025593933","display_name":"Alexey Gorodilov","orcid":null},"institutions":[{"id":"https://openalex.org/I58957048","display_name":"Yandex (Russia)","ror":"https://ror.org/04dbch786","country_code":"RU","type":"company","lineage":["https://openalex.org/I58957048"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Gorodilov","raw_affiliation_strings":["Yandex, Moscow, Russian Fed","Yandex, Moscow, Russian Fed.#TAB#"],"affiliations":[{"raw_affiliation_string":"Yandex, Moscow, Russian Fed","institution_ids":[]},{"raw_affiliation_string":"Yandex, Moscow, Russian Fed.#TAB#","institution_ids":["https://openalex.org/I58957048"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111076280","display_name":"Cliff Brunk","orcid":null},"institutions":[{"id":"https://openalex.org/I58957048","display_name":"Yandex (Russia)","ror":"https://ror.org/04dbch786","country_code":"RU","type":"company","lineage":["https://openalex.org/I58957048"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Cliff A. Brunk","raw_affiliation_strings":["Yandex, Palo Alto, CA, USA","Yandex, Palo Alto, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yandex, Palo Alto, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Yandex, Palo Alto, CA, USA#TAB#","institution_ids":["https://openalex.org/I58957048"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110057155"],"corresponding_institution_ids":["https://openalex.org/I58957048"],"apc_list":null,"apc_paid":null,"fwci":2.7063,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90928584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1897","last_page":"1900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9940000176429749,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9940000176429749,"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/T10028","display_name":"Topic Modeling","score":0.9902999997138977,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9890999794006348,"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/boosting","display_name":"Boosting (machine learning)","score":0.8536590337753296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7539950609207153},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6915034651756287},{"id":"https://openalex.org/keywords/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.6809126138687134},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6426041722297668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5991787314414978},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.5451397895812988},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.43531113862991333},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3946273922920227},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.3628746271133423},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19909927248954773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11784791946411133},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11363384127616882},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08151286840438843}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8536590337753296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539950609207153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6915034651756287},{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.6809126138687134},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6426041722297668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5991787314414978},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.5451397895812988},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.43531113862991333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3946273922920227},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3628746271133423},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19909927248954773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11784791946411133},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11363384127616882},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08151286840438843}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871758","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1639324152","https://openalex.org/W1678356000","https://openalex.org/W1973435495","https://openalex.org/W2129245267","https://openalex.org/W2149427297","https://openalex.org/W2159545104","https://openalex.org/W2168278308","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3204430031","https://openalex.org/W3137904399","https://openalex.org/W4310492845","https://openalex.org/W4386690025","https://openalex.org/W2885778889","https://openalex.org/W4310224730","https://openalex.org/W2766514146","https://openalex.org/W4289703016","https://openalex.org/W2885516856"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,22],"introduce":[4],"a":[5,102],"novel":[6],"machine":[7],"learning":[8],"approach":[9],"for":[10],"regression":[11,161],"based":[12],"on":[13,53,81,105],"the":[14,117,120,132,144,158,163],"idea":[15],"of":[16,100,116,131,138,160],"combining":[17],"bagging":[18,47,71],"and":[19,38,41,59,93,113,128,175],"boosting":[20,36],"that":[21,61,88,148],"call":[23],"BagBoo.":[24],"Our":[25],"BagBoo":[26,62,89,165],"model":[27,166],"borrows":[28],"its":[29],"high":[30,39],"accuracy":[31],"potential":[32],"from.":[33],"Friedman's":[34],"gradient":[35],"[2],":[37],"efficiency":[40],"scalability":[42],"through":[43],"parallelism":[44],"from":[45],"Breiman's":[46],"[1].":[48],"We":[49,85,142],"run":[50],"empirical":[51],"evaluations":[52],"large":[54],"scale":[55],"Web":[56],"ranking":[57],"data,":[58],"demonstrate":[60],"is":[63,90,167],"not":[64],"only":[65],"showing":[66],"superior":[67],"relevance":[68,123],"than":[69],"standalone":[70],"or":[72],"boosting,":[73],"but":[74],"also":[75,86],"outperforms":[76],"most":[77],"previously":[78],"published":[79],"results":[80,153],"these":[82],"data":[83],"sets.":[84],"emphasize":[87],"intrinsically":[91],"scalable":[92],"parallelizable,":[94],"allowing":[95],"us":[96],"to":[97,169],"train":[98],"order":[99],"half":[101],"million":[103],"trees":[104],"200":[106],"nodes":[107],"in":[108,119,135,157],"2":[109],"hours":[110],"CPU":[111],"time":[112],"beat":[114],"all":[115],"competitors":[118],"Internet":[121],"Mathematics":[122],"competition":[124],"sponsored":[125],"by":[126,146],"Yandex":[127],"be":[129],"one":[130],"top":[133],"algorithms":[134],"both":[136],"tracks":[137],"Yahoo":[139],"ICML-2010":[140],"challenge.":[141],"conclude":[143],"paper":[145],"stating":[147],"while":[149],"impressive":[150],"experimental":[151],"evaluation":[152],"are":[154],"presented":[155],"here":[156],"context":[159],"trees,":[162],"hybrid":[164],"applicable":[168],"other":[170],"domains,":[171],"such":[172],"as":[173],"classification,":[174],"base":[176],"training":[177],"models.":[178]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}