{"id":"https://openalex.org/W2103040786","doi":"https://doi.org/10.1145/502512.502521","title":"The \"DGX\" distribution for mining massive, skewed data","display_name":"The \"DGX\" distribution for mining massive, skewed data","publication_year":2001,"publication_date":"2001-08-26","ids":{"openalex":"https://openalex.org/W2103040786","doi":"https://doi.org/10.1145/502512.502521","mag":"2103040786"},"language":"en","primary_location":{"id":"doi:10.1145/502512.502521","doi":"https://doi.org/10.1145/502512.502521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/502512.502521","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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":null,"display_name":"Zhiqiang Bi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqiang Bi","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035605036","display_name":"Christos Faloutsos","orcid":"https://orcid.org/0000-0003-2996-9790","observed_orcids":["https://orcid.org/0000-0003-2996-9790"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos Faloutsos","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110197814","display_name":"Flip R. Korn","orcid":"https://orcid.org/0000-0002-4689-3225","observed_orcids":["https://orcid.org/0000-0002-4689-3225"]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Flip Korn","raw_affiliation_strings":["AT&T Labs-Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.7725,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.99647887,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10968","display_name":"Statistical Distribution Estimation and Applications","score":0.8515999913215637,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10968","display_name":"Statistical Distribution Estimation and Applications","score":0.8515999913215637,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13500","display_name":"Probability and Statistical Research","score":0.05400000140070915,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12261","display_name":"Statistical Mechanics and Entropy","score":0.016699999570846558,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/skewed-distributions","display_name":"skewed distributions","score":0.7910000085830688},{"id":"https://openalex.org/keywords/zipf-distribution","display_name":"Zipf distribution","score":0.8140000104904175},{"id":"https://openalex.org/keywords/distribution-fitting","display_name":"distribution fitting","score":0.675000011920929},{"id":"https://openalex.org/keywords/maximum-likelihood-estimation","display_name":"maximum likelihood estimation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/parameter-estimation","display_name":"parameter estimation","score":0.671999990940094},{"id":"https://openalex.org/keywords/sales-data","display_name":"sales data","score":0.5329999923706055},{"id":"https://openalex.org/keywords/usage-data","display_name":"usage data","score":0.8740000128746033},{"id":"https://openalex.org/keywords/clickstream-data","display_name":"clickstream data","score":0.9399999976158142},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.8949999809265137},{"id":"https://openalex.org/keywords/data-mining","display_name":"data mining","score":0.5830000042915344}],"concepts":[{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.8034121990203857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6303025484085083},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5982553362846375},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5877261161804199},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.5377514362335205},{"id":"https://openalex.org/C1602530","wikidata":"https://www.wikidata.org/wiki/Q1472677","display_name":"Heavy-tailed distribution","level":3,"score":0.4799773693084717},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.41957664489746094},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.379415899515152},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.379025936126709},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3773367702960968},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22800353169441223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18478646874427795}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/502512.502521","doi":"https://doi.org/10.1145/502512.502521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/502512.502521","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.8881","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.8881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~christos/PUBLICATIONS/dgx-sigkdd2001.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.7887","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.7887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~christos/PUBLICATIONS/dgx-sigkdd2001.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.1810","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.1810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.db.cs.cmu.edu/db-site/Pubs/Lib/kdd01dgx/kdd01_dgx.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.4314","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.4314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.informedia.cs.cmu.edu/documents/zhiqiang-sigkdd01-dgx.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1495007564","https://openalex.org/W1529740232","https://openalex.org/W1543886729","https://openalex.org/W1965656829","https://openalex.org/W2001697496","https://openalex.org/W2005947440","https://openalex.org/W2009351010","https://openalex.org/W2014166098","https://openalex.org/W2036671379","https://openalex.org/W2041258965","https://openalex.org/W2048392910","https://openalex.org/W2083307850","https://openalex.org/W2099482420","https://openalex.org/W2112053513","https://openalex.org/W2135869163","https://openalex.org/W2144684817","https://openalex.org/W2321470647","https://openalex.org/W2949525215","https://openalex.org/W3146507833","https://openalex.org/W4249676434","https://openalex.org/W6629777733"],"related_works":["https://openalex.org/W4405801607","https://openalex.org/W4401192494","https://openalex.org/W1987487696","https://openalex.org/W4389059941","https://openalex.org/W1696999315","https://openalex.org/W1672247054","https://openalex.org/W7167039620","https://openalex.org/W4385886675","https://openalex.org/W151938044","https://openalex.org/W1866277475"],"abstract_inverted_index":{"Skewed":[0],"distributions":[1,105],"appear":[2],"very":[3,106,121],"often":[4,12],"in":[5,36,99,114],"practice.":[6],"Unfortunately,":[7],"the":[8,27,46,61,131,136],"traditional":[9],"Zipf":[10,47],"distribution":[11,44,48],"fails":[13],"to":[14,32,73],"model":[15],"them":[16],"well.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,134],"propose":[22],"a":[23,37,50,55,74,87,110,127,141],"new":[24,43,142],"probability":[25],"distribution,":[26],"Discrete":[28],"Gaussian":[29],"Exponential":[30],"(DGX),":[31],"achieve":[33],"excellent":[34],"fits":[35,103],"wide":[38,75],"variety":[39,76],"of":[40,77,138],"settings;":[41],"our":[42],"includes":[45],"as":[49,83,140,149],"special":[51],"case.":[52],"We":[53,70],"present":[54],"statistically":[56],"sound":[57],"method":[58],"for":[59,144],"estimating":[60],"DGX":[62,72,102,139],"parameters":[63],"based":[64],"on":[65],"maximum":[66],"likelihood":[67],"estimation":[68],"(MLE).":[69],"applied":[71],"real":[78],"world":[79],"data":[80,85,92,145],"sets,":[81],"such":[82,148],"sales":[84],"from":[86,93],"large":[88],"retailer":[89],"chain,":[90],"us-age":[91],"AT&T,":[94],"and":[95],"Internet":[96],"clickstream":[97],"data;":[98],"all":[100],"cases,":[101],"these":[104],"well,":[107],"with":[108],"almost":[109],"99%":[111],"correlation":[112],"coefficient":[113],"quantile-quantile":[115],"plots.":[116],"Our":[117],"algorithm":[118],"also":[119],"scales":[120],"well":[122],"because":[123],"it":[124],"requires":[125],"only":[126],"single":[128],"pass":[129],"over":[130],"data.":[132],"Finally,":[133],"illustrate":[135],"power":[137],"tool":[143],"mining":[146],"tasks,":[147],"outlier":[150],"detection.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":10}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}