{"id":"https://openalex.org/W2140811298","doi":"https://doi.org/10.14778/2556549.2556557","title":"Scalable progressive analytics on big data in the cloud","display_name":"Scalable progressive analytics on big data in the cloud","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2140811298","doi":"https://doi.org/10.14778/2556549.2556557","mag":"2140811298"},"language":"en","primary_location":{"id":"doi:10.14778/2556549.2556557","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2556549.2556557","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/A5067654293","display_name":"Badrish Chandramouli","orcid":"https://orcid.org/0000-0002-8468-4037"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Badrish Chandramouli","raw_affiliation_strings":["Microsoft Research, Redmond","Microsoft Research (Redmond)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research (Redmond)#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111492493","display_name":"Jonathan Goldstein","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jonathan Goldstein","raw_affiliation_strings":["Microsoft Research, Redmond","Microsoft Research (Redmond)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research (Redmond)#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034722698","display_name":"Abdul Quamar","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdul Quamar","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.7169,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.9888365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":"14","first_page":"1726","last_page":"1737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987000226974487,"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/T11106","display_name":"Data Management and Algorithms","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8604122400283813},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7231258153915405},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6726614832878113},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.669161319732666},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.665973424911499},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5334102511405945},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.460714191198349},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4161655604839325},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40891098976135254},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37532785534858704},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3294829726219177},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3073883056640625},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15305548906326294},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1047581136226654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8604122400283813},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7231258153915405},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6726614832878113},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.669161319732666},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.665973424911499},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5334102511405945},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.460714191198349},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4161655604839325},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40891098976135254},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37532785534858704},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3294829726219177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3073883056640625},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15305548906326294},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1047581136226654}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2556549.2556557","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2556549.2556557","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1598064945","https://openalex.org/W1964857063","https://openalex.org/W1993755553","https://openalex.org/W2001474264","https://openalex.org/W2003580796","https://openalex.org/W2020147322","https://openalex.org/W2035801804","https://openalex.org/W2038669746","https://openalex.org/W2071989194","https://openalex.org/W2074935284","https://openalex.org/W2090415144","https://openalex.org/W2090673017","https://openalex.org/W2099601885","https://openalex.org/W2115503987","https://openalex.org/W2121142115","https://openalex.org/W2126982545","https://openalex.org/W2131166445","https://openalex.org/W2131975293","https://openalex.org/W2137901744","https://openalex.org/W2140509629","https://openalex.org/W2140811298","https://openalex.org/W2145385038","https://openalex.org/W2151023586","https://openalex.org/W2151065878","https://openalex.org/W2155960838","https://openalex.org/W2164507334","https://openalex.org/W2165962877","https://openalex.org/W2167274498","https://openalex.org/W2170833472","https://openalex.org/W2171828861","https://openalex.org/W2173213060","https://openalex.org/W2294541523","https://openalex.org/W2296677182","https://openalex.org/W2912802084","https://openalex.org/W2953310312","https://openalex.org/W4229903866","https://openalex.org/W4237172715","https://openalex.org/W4237421257","https://openalex.org/W4254259096","https://openalex.org/W4301895403","https://openalex.org/W6650951000","https://openalex.org/W6677231548","https://openalex.org/W6678853867","https://openalex.org/W6697454124"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2910064364","https://openalex.org/W4200136508","https://openalex.org/W2019038080"],"abstract_inverted_index":{"Analytics":[0],"over":[1,122,201,224],"the":[2,9,18,61,68,83,113,183,215],"increasing":[3,30],"quantity":[4],"of":[5,29,63,219],"data":[6,31,132],"stored":[7],"in":[8,56,182,190],"Cloud":[10,20],"has":[11],"become":[12],"very":[13],"expensive,":[14],"particularly":[15],"due":[16],"to":[17,108,112,131,157,197],"pay-as-you-go":[19],"computation":[21,169],"model.":[22],"Data":[23],"scientists":[24],"typically":[25],"manually":[26],"extract":[27],"samples":[28,111],"size":[32],"(progressive":[33],"samples)":[34],"using":[35,146],"domain-specific":[36],"sampling":[37],"strategies":[38],"for":[39,86,142,171,227],"exploratory":[40],"querying.":[41],"This":[42],"provides":[43,126],"them":[44],"with":[45,187,194,209],"user-control,":[46],"repeatable":[47,127],"semantics,":[48],"and":[49,118,124,129,211,217,221],"result":[50,55],"provenance.":[51],"However,":[52],"such":[53],"solutions":[54,226],"tedious":[57],"workflows":[58],"that":[59,104,136],"preclude":[60],"reuse":[62],"work":[64],"across":[65],"samples.":[66],"On":[67],"other":[69],"hand,":[70],"existing":[71],"approximate":[72],"query":[73,120],"processing":[74,121],"systems":[75],"report":[76],"early":[77],"results,":[78],"but":[79],"do":[80],"not":[81],"offer":[82],"above":[84],"benefits":[85,218],"complex":[87],"ad-hoc":[88],"queries.":[89],"We":[90,134],"propose":[91],"a":[92,99,166,179],"new":[93],"progressive":[94,110,167,199,228],"analytics":[95],"system":[96],"based":[97],"on":[98,161,206],"progress":[100,175],"model":[101,141],"called":[102],"Prism":[103],"(1)":[105],"allows":[106,116],"users":[107],"communicate":[109],"system;":[114],"(2)":[115],"efficient":[117],"deterministic":[119],"samples;":[123],"(3)":[125],"semantics":[128],"provenance":[130],"scientists.":[133],"show":[135],"one":[137],"can":[138],"realize":[139],"this":[140],"atemporal":[143],"relational":[144],"queries":[145],"an":[147],"unmodified":[148],"temporal":[149,154],"streaming":[150,195],"engine,":[151],"by":[152],"re-interpreting":[153],"event":[155],"fields":[156],"denote":[158],"progress.":[159],"Based":[160],"Prism,":[162],"we":[163],"build":[164],"Now!,":[165],"data-parallel":[168],"framework":[170],"Windows":[172,207],"Azure,":[173],"where":[174],"is":[176],"understood":[177],"as":[178],"first-class":[180],"citizen":[181],"framework.":[184],"Now!":[185,220],"works":[186,193],"\"progress-aware":[188],"reducers\"-":[189],"particular,":[191],"it":[192],"engines":[196],"support":[198],"SQL":[200],"big":[202],"data.":[203],"Extensive":[204],"experiments":[205],"Azure":[208],"real":[210],"synthetic":[212],"workloads":[213],"validate":[214],"scalability":[216],"its":[222],"optimizations,":[223],"current":[225],"analytics.":[229]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}