{"id":"https://openalex.org/W2292590056","doi":"https://doi.org/10.14778/2824032.2824087","title":"Demonstration of Santoku","display_name":"Demonstration of Santoku","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2292590056","doi":"https://doi.org/10.14778/2824032.2824087","mag":"2292590056"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824087","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824087","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/A5103749365","display_name":"Arun Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Kumar","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038525771","display_name":"Mona Jalal","orcid":"https://orcid.org/0000-0001-9904-9354"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Jalal","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073720496","display_name":"Boqun Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boqun Yan","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017678555","display_name":"Jeffrey F. Naughton","orcid":"https://orcid.org/0000-0002-3710-8096"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Naughton","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":3.9288,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94405732,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":"12","first_page":"1864","last_page":"1867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13398","display_name":"Data Analysis with R","score":0.9954000115394592,"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"}},"topics":[{"id":"https://openalex.org/T13398","display_name":"Data Analysis with R","score":0.9954000115394592,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9925000071525574,"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/T11719","display_name":"Data Quality and Management","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.844542384147644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8074573874473572},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6836397647857666},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6593672037124634},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6572465300559998},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.6326771974563599},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.602082371711731},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4848831593990326},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.46672263741493225},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4479932188987732},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4305129945278168},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39655372500419617},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13946068286895752},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0927760899066925}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.844542384147644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074573874473572},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6836397647857666},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6593672037124634},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6572465300559998},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6326771974563599},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.602082371711731},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4848831593990326},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.46672263741493225},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4479932188987732},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4305129945278168},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39655372500419617},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13946068286895752},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0927760899066925},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2824032.2824087","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824087","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2032775418","https://openalex.org/W2096689597","https://openalex.org/W2099102906","https://openalex.org/W2406996511","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W2067184662","https://openalex.org/W3047837489","https://openalex.org/W2622139626","https://openalex.org/W2982321410","https://openalex.org/W2133660117","https://openalex.org/W2104496206","https://openalex.org/W95465806"],"abstract_inverted_index":{"Advanced":[0],"analytics":[1],"is":[2,29,76,138,146],"a":[3,12,30,53,88,141,147],"booming":[4],"area":[5],"in":[6,78,143,159],"the":[7,27,94,103,155],"data":[8,81],"management":[9],"industry":[10],"and":[11,108,163],"hot":[13],"research":[14],"topic.":[15],"Almost":[16],"all":[17],"toolkits":[18,67],"that":[19,26,129],"implement":[20],"machine":[21],"learning":[22,79,107],"(ML)":[23],"algorithms":[24],"assume":[25],"input":[28],"single":[31,41],"table,":[32],"but":[33],"most":[34],"relational":[35],"datasets":[36],"are":[37],"not":[38,69],"stored":[39],"as":[40,140],"tables":[42,50],"due":[43],"to":[44,51,90,112,125],"normalization.":[45],"Thus,":[46],"analysts":[47,57,92,132,165],"often":[48],"join":[49],"obtain":[52],"denormalized":[54],"table.":[55],"Also,":[56],"typically":[58],"ignore":[59],"any":[60],"functional":[61],"dependencies":[62,124],"among":[63],"features":[64],"because":[65],"ML":[66,97,116,161],"do":[68],"support":[70],"them.":[71],"In":[72],"both":[73],"cases,":[74],"time":[75],"wasted":[77],"over":[80,98],"with":[82,133,166],"redundancy.":[83],"We":[84,153],"demonstrate":[85,154],"Santoku":[86,101,120,158],",":[87],"toolkit":[89],"help":[91,131],"improve":[93],"performance":[95,162],"of":[96,105,157],"normalized":[99],"data.":[100],"applies":[102],"idea":[104],"factorized":[106],"automatically":[109],"decides":[110],"whether":[111],"denormalize":[113],"or":[114],"push":[115],"computations":[117],"through":[118],"joins.":[119],"also":[121],"exploits":[122],"database":[123],"provide":[126],"automatic":[127],"insights":[128],"could":[130],"exploratory":[134],"feature":[135,167],"selection.":[136,168],"It":[137],"usable":[139],"library":[142],"R,":[144],"which":[145],"popular":[148],"environment":[149],"for":[150],"advanced":[151],"analytics.":[152],"benefits":[156],"improving":[160],"helping":[164]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}