{"id":"https://openalex.org/W1990388336","doi":"https://doi.org/10.1145/1008694.1008700","title":"Horizontal aggregations for building tabular data sets","display_name":"Horizontal aggregations for building tabular data sets","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W1990388336","doi":"https://doi.org/10.1145/1008694.1008700","mag":"1990388336"},"language":"en","primary_location":{"id":"doi:10.1145/1008694.1008700","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008694.1008700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery","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/A5031610238","display_name":"Carlos Ordo\u0144\u1ebdz","orcid":"https://orcid.org/0009-0005-1135-9726"},"institutions":[{"id":"https://openalex.org/I4210158714","display_name":"Teradata (United States)","ror":"https://ror.org/04vkkat38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210158714"]},{"id":"https://openalex.org/I108650528","display_name":"Teradata (United Kingdom)","ror":"https://ror.org/00gze1672","country_code":"GB","type":"company","lineage":["https://openalex.org/I108650528","https://openalex.org/I4210158714"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Carlos Ordonez","raw_affiliation_strings":["Teradata, NCR, San Diego, CA","Teradata (NCR), San Diego, CA"],"affiliations":[{"raw_affiliation_string":"Teradata, NCR, San Diego, CA","institution_ids":["https://openalex.org/I4210158714"]},{"raw_affiliation_string":"Teradata (NCR), San Diego, CA","institution_ids":["https://openalex.org/I108650528"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031610238"],"corresponding_institution_ids":["https://openalex.org/I108650528","https://openalex.org/I4210158714"],"apc_list":null,"apc_paid":null,"fwci":0.2857,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.56037184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.7908947467803955},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7009238004684448},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6916568279266357},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6221194863319397},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5904969573020935},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5741466879844666},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5306006669998169},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5221602916717529},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5046170949935913},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.48418310284614563},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43223798274993896},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4221777319908142},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4154413938522339},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36467814445495605},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14273419976234436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1373586654663086},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11464011669158936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908947467803955},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7009238004684448},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6916568279266357},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6221194863319397},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5904969573020935},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5741466879844666},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5306006669998169},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5221602916717529},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5046170949935913},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.48418310284614563},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43223798274993896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4221777319908142},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4154413938522339},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36467814445495605},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14273419976234436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1373586654663086},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11464011669158936},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1008694.1008700","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008694.1008700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.701.4073","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.701.4073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.cs.uh.edu/%7Eordonez/w-pdf/w-2004-DMKD-horagg.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W843410015","https://openalex.org/W1487902141","https://openalex.org/W1994674921","https://openalex.org/W1995999642","https://openalex.org/W1996006113","https://openalex.org/W2019916408","https://openalex.org/W2026450968","https://openalex.org/W2045466225","https://openalex.org/W2049578111","https://openalex.org/W2054638878","https://openalex.org/W2060947232","https://openalex.org/W2063680791","https://openalex.org/W2064803206","https://openalex.org/W2071089166","https://openalex.org/W2072191579","https://openalex.org/W2102951036","https://openalex.org/W2103139809","https://openalex.org/W2103201239","https://openalex.org/W2122789628","https://openalex.org/W2143979434","https://openalex.org/W2144405306","https://openalex.org/W2152592483","https://openalex.org/W2166559705","https://openalex.org/W2185907055","https://openalex.org/W2206925937","https://openalex.org/W2291125829","https://openalex.org/W2988119170","https://openalex.org/W4248008732"],"related_works":["https://openalex.org/W2573939812","https://openalex.org/W2120098008","https://openalex.org/W1639806124","https://openalex.org/W4366145086","https://openalex.org/W2902831276","https://openalex.org/W2540682188","https://openalex.org/W4385834214","https://openalex.org/W3022423983","https://openalex.org/W12347151","https://openalex.org/W2957025774"],"abstract_inverted_index":{"In":[0,20],"a":[1,5,14,21,47,64,80,105],"data":[2,15,27,72,76,145,150,195],"mining":[3,77,146],"project,":[4],"significant":[6,65],"portion":[7],"of":[8,107,110,120],"time":[9],"is":[10,67,83,138,178],"devoted":[11],"to":[12,70,94,98,168],"building":[13,25,127],"set":[16,28,106],"suitable":[17,74],"for":[18,56,75],"analysis.":[19],"relational":[22,182],"database":[23],"environment,":[24],"such":[26],"usually":[29],"requires":[30],"joining":[31],"tables":[32],"and":[33,157,184],"aggregating":[34],"columns":[35],"with":[36,193],"SQL":[37,40,95],"queries.":[38],"Existing":[39],"aggregations":[41,61,100,125,171],"are":[42,153],"limited":[43],"since":[44],"they":[45],"return":[46],"single":[48],"number":[49,112],"per":[50,113],"aggregated":[51],"group,":[52],"producing":[53],"one":[54,111,187],"row":[55],"each":[57],"computed":[58],"number.":[59],"These":[60],"help,":[62],"but":[63],"effort":[66],"still":[68],"required":[69],"build":[71],"sets":[73,129,196],"purposes,":[78],"where":[79],"tabular":[81,102,131],"format":[82],"generally":[84],"required.":[85],"This":[86],"work":[87],"proposes":[88],"very":[89],"simple,":[90],"yet":[91],"powerful,":[92],"extensions":[93],"aggregate":[96],"functions":[97,121],"produce":[99],"in":[101,130],"form,":[103],"returning":[104],"numbers":[108],"instead":[109],"row.":[114],"We":[115,164],"call":[116],"this":[117],"new":[118],"class":[119],"horizontal":[122,170],"aggregations.":[123],"Horizontal":[124],"help":[126],"answer":[128],"form":[132,141],"(e.g.":[133],"point-dimension,":[134],"observation-variable,":[135],"instance-feature),":[136],"which":[137],"the":[139,185,189,198],"standard":[140,173],"needed":[142],"by":[143],"most":[144],"algorithms.":[147],"Two":[148],"common":[149],"preparation":[151],"tasks":[152],"explained,":[154],"including":[155],"transposition/aggregation":[156],"transforming":[158],"categorical":[159],"attributes":[160],"into":[161],"binary":[162],"dimensions.":[163],"propose":[165],"two":[166],"strategies":[167],"evaluate":[169],"using":[172],"SQL.":[174],"The":[175],"first":[176],"strategy":[177],"based":[179],"only":[180],"on":[181],"operators":[183],"second":[186],"uses":[188],"\"case\"":[190],"construct.":[191],"Experiments":[192],"large":[194],"study":[197],"proposed":[199],"query":[200],"optimization":[201],"strategies.":[202]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}