{"id":"https://openalex.org/W2775492453","doi":"https://doi.org/10.1186/s40537-017-0107-2","title":"Scaling associative classification for very large datasets","display_name":"Scaling associative classification for very large datasets","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2775492453","doi":"https://doi.org/10.1186/s40537-017-0107-2","mag":"2775492453"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-017-0107-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0107-2","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-017-0107-2","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-017-0107-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Luca Venturini","orcid":"https://orcid.org/0000-0003-1349-0494"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Luca Venturini","raw_affiliation_strings":["Department of Control and Computer Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, Torino, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1349-0494","affiliations":[{"raw_affiliation_string":"Department of Control and Computer Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Elena Baralis","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elena Baralis","raw_affiliation_strings":["Department of Control and Computer Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Computer Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":null,"display_name":"Paolo Garza","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Garza","raw_affiliation_strings":["Department of Control and Computer Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Computer Engineering, Politecnico di Torino, Corso Duca degli Abruzzi 24, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":3.4717,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94092549,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.28780001401901245,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.28780001401901245,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.15479999780654907,"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/T14347","display_name":"Big Data and Digital Economy","score":0.06390000134706497,"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/scalability","display_name":"Scalability","score":0.7774999737739563},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7170000076293945},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6830000281333923},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6725000143051147},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.6338000297546387},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5781000256538391},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4575999975204468},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.44130000472068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8729000091552734},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7774999737739563},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7170000076293945},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6830000281333923},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6725000143051147},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.6338000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5896999835968018},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5781000256538391},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5771999955177307},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.35440000891685486},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2709999978542328}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s40537-017-0107-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0107-2","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-017-0107-2","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1805.03887","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.03887","pdf_url":"https://arxiv.org/pdf/1805.03887","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":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:51ddf890fe7e47ab8e433aa6acadc341","is_oa":true,"landing_page_url":"https://doaj.org/article/51ddf890fe7e47ab8e433aa6acadc341","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 4, Iss 1, Pp 1-24 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-017-0107-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0107-2","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-017-0107-2","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1183871506","display_name":null,"funder_award_id":"700256","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8610984188","display_name":"Improving Resilience to Emergencies through Advanced Cyber Technologies","funder_award_id":"700256","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2775492453.pdf","grobid_xml":"https://content.openalex.org/works/W2775492453.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1488440450","https://openalex.org/W1528447234","https://openalex.org/W1570448133","https://openalex.org/W1623342295","https://openalex.org/W1907020532","https://openalex.org/W1917795079","https://openalex.org/W2026248097","https://openalex.org/W2056910091","https://openalex.org/W2070996757","https://openalex.org/W2108923196","https://openalex.org/W2118020653","https://openalex.org/W2121456247","https://openalex.org/W2122076457","https://openalex.org/W2126623642","https://openalex.org/W2136565860","https://openalex.org/W2138061404","https://openalex.org/W2145611520","https://openalex.org/W2155653793","https://openalex.org/W2160605849","https://openalex.org/W2170677240","https://openalex.org/W2295598076","https://openalex.org/W2510233260","https://openalex.org/W2748831951","https://openalex.org/W4239115086","https://openalex.org/W6614148910","https://openalex.org/W6675354045"],"related_works":[],"abstract_inverted_index":{"Supervised":[0],"learning":[1,63],"algorithms":[2],"are":[3,11,35],"nowadays":[4],"successfully":[5],"scaling":[6],"up":[7],"to":[8,64,89],"datasets":[9,27],"that":[10,137],"very":[12],"large":[13],"in":[14,104,144],"volume,":[15],"leveraging":[16],"the":[17,66,77,81,105,152,169,172,175,178],"potential":[18],"of":[19,31,68,80,101,177],"in-memory":[20],"cluster-computing":[21],"Big":[22],"Data":[23],"frameworks.":[24],"Still,":[25],"massive":[26],"with":[28,47,123],"a":[29,36,56,98,119,141,181],"number":[30],"large-domain":[32],"categorical":[33],"features":[34],"difficult":[37],"challenge":[38],"for":[39,184],"any":[40],"classifier.":[41],"Most":[42],"off-the-shelf":[43],"solutions":[44],"cannot":[45],"cope":[46],"this":[48,51],"problem.":[49],"In":[50],"work":[52],"we":[53],"introduce":[54],"DAC,":[55],"Distributed":[57],"Associative":[58],"Classifier.":[59],"DAC":[60,138],"exploits":[61],"ensemble":[62],"distribute":[65],"training":[67],"an":[69],"associative":[70],"classifier":[71],"among":[72,96],"parallel":[73],"workers":[74],"and":[75,129,148,174],"improve":[76],"final":[78],"quality":[79,147],"model.":[82],"Furthermore,":[83],"it":[84,157],"adopts":[85],"several":[86],"novel":[87],"techniques":[88],"reach":[90],"high":[91],"scalability":[92],"without":[93],"sacrificing":[94],"quality,":[95],"which":[97],"preventive":[99],"pruning":[100],"classification":[102],"rules":[103],"extraction":[106],"phase":[107],"based":[108],"on":[109,115,118,140],"Gini":[110],"impurity.":[111],"We":[112],"ran":[113],"experiments":[114],"Apache":[116],"Spark,":[117],"real":[120],"large-scale":[121],"dataset":[122],"more":[124],"than":[125],"4":[126],"billion":[127],"records":[128],"800":[130],"million":[131],"distinct":[132],"categories.":[133],"The":[134],"results":[135],"showed":[136],"improves":[139],"state-of-the-art":[142],"solution":[143],"both":[145,168],"prediction":[146,173],"execution":[149],"time.":[150],"Since":[151],"generated":[153],"model":[154],"is":[155],"human-readable,":[156],"can":[158],"not":[159],"only":[160],"classify":[161],"new":[162],"records,":[163],"but":[164],"also":[165],"allow":[166],"understanding":[167],"logic":[170],"behind":[171],"properties":[176],"model,":[179],"becoming":[180],"useful":[182],"aid":[183],"decision":[185],"makers.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-10T07:45:09.275182","created_date":"2017-12-22T00:00:00"}