{"id":"https://openalex.org/W2131020804","doi":"https://doi.org/10.1145/1014052.1014090","title":"Exploiting a support-based upper bound of Pearson's correlation coefficient for efficiently identifying strongly correlated pairs","display_name":"Exploiting a support-based upper bound of Pearson's correlation coefficient for efficiently identifying strongly correlated pairs","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2131020804","doi":"https://doi.org/10.1145/1014052.1014090","mag":"2131020804"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth 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/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["University of Minnesota"],"affiliations":[{"raw_affiliation_string":"University of Minnesota","institution_ids":["https://openalex.org/I2800403580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102940260","display_name":"Shashi Shekhar","orcid":"https://orcid.org/0000-0002-3191-3879"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shashi Shekhar","raw_affiliation_strings":["University of Minnesota"],"affiliations":[{"raw_affiliation_string":"University of Minnesota","institution_ids":["https://openalex.org/I2800403580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071546444","display_name":"Pang\u2010Ning Tan","orcid":"https://orcid.org/0000-0003-3205-0339"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pang-Ning Tan","raw_affiliation_strings":["Michigan State University"],"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645812","display_name":"Vipin Kumar","orcid":"https://orcid.org/0000-0002-9040-2665"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vipin Kumar","raw_affiliation_strings":["University of Minnesota"],"affiliations":[{"raw_affiliation_string":"University of Minnesota","institution_ids":["https://openalex.org/I2800403580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101862104"],"corresponding_institution_ids":["https://openalex.org/I2800403580"],"apc_list":null,"apc_paid":null,"fwci":14.5345,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.98436758,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"334","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9936000108718872,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6628812551498413},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.5868470668792725},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5759234428405762},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5639050006866455},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.5143228769302368},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5074202418327332},{"id":"https://openalex.org/keywords/monotone-polygon","display_name":"Monotone polygon","score":0.44346296787261963},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4410057067871094},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42318400740623474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.34590062499046326},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2359413504600525}],"concepts":[{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6628812551498413},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.5868470668792725},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5759234428405762},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5639050006866455},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.5143228769302368},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5074202418327332},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.44346296787261963},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4410057067871094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42318400740623474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34590062499046326},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2359413504600525},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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:10.1145/1014052.1014090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1510033442","https://openalex.org/W1533168323","https://openalex.org/W1568971298","https://openalex.org/W1888464276","https://openalex.org/W1965731052","https://openalex.org/W1969842215","https://openalex.org/W1988332933","https://openalex.org/W2041258965","https://openalex.org/W2052411822","https://openalex.org/W2064853889","https://openalex.org/W2083991698","https://openalex.org/W2108560469","https://openalex.org/W2140129471","https://openalex.org/W2166559705","https://openalex.org/W2167482307","https://openalex.org/W2210278139","https://openalex.org/W2321470647","https://openalex.org/W3023428462","https://openalex.org/W3203501156","https://openalex.org/W4245913787","https://openalex.org/W4252403066","https://openalex.org/W6631752645"],"related_works":["https://openalex.org/W357196361","https://openalex.org/W2027314909","https://openalex.org/W3109425891","https://openalex.org/W3096637473","https://openalex.org/W1036938216","https://openalex.org/W2113714434","https://openalex.org/W2377792686","https://openalex.org/W4200439127","https://openalex.org/W829658220","https://openalex.org/W2946560178"],"abstract_inverted_index":{"Given":[0],"a":[1,8,84,116],"user-specified":[2],"minimum":[3],"correlation":[4,20,62,79],"threshold":[5,30],"\u03b8":[6],"and":[7,15,38,159,166],"market":[9],"basket":[10],"database":[11],"with":[12,26,148],"N":[13],"items":[14,37,142],"T":[16],"transactions,":[17],"an":[18,57,122,174],"all-strong-pairs":[19],"query":[21,47],"finds":[22],"all":[23],"item":[24,93],"pairs":[25,94],"correlations":[27],"above":[28],"the":[29,34,42,129,139,169],"\u03b8.":[31],"However,":[32],"when":[33,138],"number":[35,140],"of":[36,45,60,91,141,176],"transactions":[39],"are":[40],"large,":[41],"computation":[43,130],"cost":[44,124],"this":[46,53],"can":[48,172],"be":[49,173],"very":[50],"high.":[51],"In":[52],"paper,":[54],"we":[55,120],"identify":[56],"upper":[58,68,99],"bound":[59,69],"Pearson's":[61,78],"coefficient":[63,80],"for":[64],"binary":[65],"variables.":[66],"This":[67],"is":[70,109,134,143],"not":[71],"only":[72],"much":[73],"cheaper":[74],"to":[75,111],"compute":[76],"than":[77,179],"but":[81],"also":[82],"exhibits":[83],"special":[85],"monotone":[86],"property":[87],"which":[88,126],"allows":[89],"pruning":[90,133],"many":[92],"even":[95],"without":[96],"computing":[97],"their":[98],"bounds.":[100],"A":[101],"Two-step":[102],"All-strong-Pairs":[103],"corrElation":[104],"que":[105],"Ry":[106],"(TAPER)":[107],"algorithm":[108,171],"proposed":[110],"exploit":[112],"these":[113],"properties":[114],"in":[115,145],"filter-and-refine":[117],"manner.":[118],"Furthermore,":[119],"provide":[121],"algebraic":[123],"model":[125],"shows":[127],"that":[128,168],"savings":[131],"from":[132,157],"independent":[135],"or":[136,151],"improves":[137],"increased":[144],"data":[146,161],"sets":[147,162],"common":[149],"Zipf":[150],"linear":[152],"rank-support":[153],"distributions.":[154],"Experimental":[155],"results":[156],"synthetic":[158],"real":[160],"exhibit":[163],"similar":[164],"trends":[165],"show":[167],"TAPER":[170],"order":[175],"magnitude":[177],"faster":[178],"brute-force":[180],"alternatives.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}