{"id":"https://openalex.org/W2568140450","doi":"https://doi.org/10.1145/2220357.2220359","title":"An Efficient Rigorous Approach for Identifying Statistically Significant Frequent Itemsets","display_name":"An Efficient Rigorous Approach for Identifying Statistically Significant Frequent Itemsets","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2568140450","doi":"https://doi.org/10.1145/2220357.2220359","mag":"2568140450"},"language":"en","primary_location":{"id":"doi:10.1145/2220357.2220359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2220357.2220359","pdf_url":null,"source":{"id":"https://openalex.org/S118992489","display_name":"Journal of the ACM","issn_l":"0004-5411","issn":["0004-5411","1557-735X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the ACM","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/A5111963396","display_name":"Adam Kirsch","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adam Kirsch","raw_affiliation_strings":["Harvard University"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062318856","display_name":"Michael Mitzenmacher","orcid":"https://orcid.org/0000-0001-5430-5457"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Mitzenmacher","raw_affiliation_strings":["Harvard University"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036587129","display_name":"Andrea Pietracaprina","orcid":"https://orcid.org/0000-0002-9189-9618"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Pietracaprina","raw_affiliation_strings":["University of Padova"],"affiliations":[{"raw_affiliation_string":"University of Padova","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048624224","display_name":"Geppino Pucci","orcid":"https://orcid.org/0000-0001-9189-6938"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Geppino Pucci","raw_affiliation_strings":["University of Padova"],"affiliations":[{"raw_affiliation_string":"University of Padova","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028869858","display_name":"Eli Upfal","orcid":"https://orcid.org/0000-0002-9321-9460"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eli Upfal","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060279781","display_name":"Fabio Vandin","orcid":"https://orcid.org/0000-0003-2244-2320"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabio Vandin","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111963396"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":6.6268,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96528183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"59","issue":"3","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":1.0,"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":1.0,"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/T11106","display_name":"Data Management and Algorithms","score":0.9961000084877014,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9884999990463257,"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":0.7291551232337952},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.717799961566925},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5702018737792969},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5007016658782959},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"False discovery rate","score":0.4709775447845459},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3289964199066162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291551232337952},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.717799961566925},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5702018737792969},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5007016658782959},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.4709775447845459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3289964199066162},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2220357.2220359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2220357.2220359","pdf_url":null,"source":{"id":"https://openalex.org/S118992489","display_name":"Journal of the ACM","issn_l":"0004-5411","issn":["0004-5411","1557-735X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the ACM","raw_type":"journal-article"},{"id":"pmh:oai:www.research.unipd.it:11577/2523845","is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?doid=2220357.2220359","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1663903143","display_name":null,"funder_award_id":"IIS-0325838DMI-0600384","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2992154628","display_name":null,"funder_award_id":"N000140610607","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5816806345","display_name":null,"funder_award_id":"15964 AEOLUS","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"},{"id":"https://openalex.org/G6076520403","display_name":null,"funder_award_id":"CNS-0721491CCF-0915922","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G8127283160","display_name":null,"funder_award_id":"IIS-0325838DMI-0600384","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G8505707357","display_name":null,"funder_award_id":"CNS-0721491CCF-0915922","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2842395","https://openalex.org/W103650626","https://openalex.org/W1511277043","https://openalex.org/W1547785593","https://openalex.org/W1558717344","https://openalex.org/W1565377632","https://openalex.org/W1585646276","https://openalex.org/W1595409123","https://openalex.org/W1596515083","https://openalex.org/W1938740620","https://openalex.org/W1965138864","https://openalex.org/W1968818631","https://openalex.org/W1979356656","https://openalex.org/W1990951910","https://openalex.org/W2000473687","https://openalex.org/W2039594635","https://openalex.org/W2059749610","https://openalex.org/W2083991698","https://openalex.org/W2103131906","https://openalex.org/W2110065044","https://openalex.org/W2110893883","https://openalex.org/W2126920781","https://openalex.org/W2129830652","https://openalex.org/W2136663836","https://openalex.org/W2140190241","https://openalex.org/W2155358700","https://openalex.org/W2163917503","https://openalex.org/W2166559705","https://openalex.org/W2899702797","https://openalex.org/W4249717268"],"related_works":["https://openalex.org/W2389124870","https://openalex.org/W1921844237","https://openalex.org/W2168149717","https://openalex.org/W200978175","https://openalex.org/W2178204436","https://openalex.org/W2113356685","https://openalex.org/W4300887971","https://openalex.org/W4293336298","https://openalex.org/W2467227750","https://openalex.org/W2118778496"],"abstract_inverted_index":{"As":[0],"advances":[1],"in":[2,32,42,87],"technology":[3],"allow":[4],"for":[5,63],"the":[6,16,22,43,68,92,98,125],"collection,":[7],"storage,":[8],"and":[9,20,97],"analysis":[10],"of":[11,14,18,24,45,70,95,127],"vast":[12],"amounts":[13],"data,":[15],"task":[17],"screening":[19],"assessing":[21],"significance":[23,41],"discovered":[25],"patterns":[26],"is":[27],"becoming":[28],"a":[29,52,57,64,79,88,113],"major":[30],"challenge":[31],"data":[33],"mining":[34],"applications.":[35],"In":[36],"this":[37],"work,":[38],"we":[39,50],"address":[40],"context":[44],"frequent":[46],"itemset":[47],"mining.":[48],"Specifically,":[49],"develop":[51],"novel":[53],"methodology":[54],"to":[55,123],"identify":[56],"meaningful":[58],"support":[59,73],"threshold":[60],"s":[61,76],"*":[62,77],"dataset,":[65],"such":[66],"that":[67],"number":[69,94],"itemsets":[71,104],"with":[72,91,112],"at":[74],"least":[75],"represents":[78],"substantial":[80],"deviation":[81],"from":[82],"what":[83],"would":[84],"be":[85,107],"expected":[86],"random":[89],"dataset":[90],"same":[93,99],"transactions":[96],"individual":[100],"item":[101],"frequencies.":[102],"These":[103],"can":[105],"then":[106],"flagged":[108],"as":[109],"statistically":[110],"significant":[111],"small":[114],"false":[115],"discovery":[116],"rate.":[117],"We":[118],"present":[119],"extensive":[120],"experimental":[121],"results":[122],"substantiate":[124],"effectiveness":[126],"our":[128],"methodology.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}