{"id":"https://openalex.org/W2013373704","doi":"https://doi.org/10.1145/1807167.1807275","title":"Ricardo","display_name":"Ricardo","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2013373704","doi":"https://doi.org/10.1145/1807167.1807275","mag":"2013373704"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807275","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","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/A5018614325","display_name":"Sudipto Das","orcid":"https://orcid.org/0009-0007-6154-1504"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sudipto Das","raw_affiliation_strings":["University of California, Santa Barbara, USA","University of California-Santa Barbara, USA;"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California-Santa Barbara, USA;","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048704801","display_name":"Yannis Sismanis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Sismanis","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104043964","display_name":"Kevin Beyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin S. Beyer","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041227178","display_name":"Rainer Gemulla","orcid":"https://orcid.org/0000-0003-2762-0050"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rainer Gemulla","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090729930","display_name":"Peter J. Haas","orcid":"https://orcid.org/0000-0001-5694-3065"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter J. Haas","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060550621","display_name":"John McPherson","orcid":"https://orcid.org/0000-0003-3371-7481"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John McPherson","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5018614325"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":19.2306,"has_fulltext":false,"cited_by_count":166,"citation_normalized_percentile":{"value":0.99546363,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"987","last_page":"998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9944999814033508,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9944999814033508,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9872999787330627,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9860000014305115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/petabyte","display_name":"Petabyte","score":0.9511851668357849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7948534488677979},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.7573580741882324},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.7216858863830566},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6778031587600708},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6607089638710022},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6115881204605103},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.534964382648468},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5335375070571899},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.5039014220237732},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4719616174697876},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43704599142074585},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4174243211746216},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3437049984931946},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3369233310222626},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3255161643028259},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17465606331825256}],"concepts":[{"id":"https://openalex.org/C13600138","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Petabyte","level":3,"score":0.9511851668357849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948534488677979},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.7573580741882324},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.7216858863830566},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6778031587600708},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6607089638710022},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6115881204605103},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.534964382648468},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5335375070571899},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.5039014220237732},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4719616174697876},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43704599142074585},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4174243211746216},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3437049984931946},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3369233310222626},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3255161643028259},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17465606331825256},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1807167.1807275","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W56918557","https://openalex.org/W1590012787","https://openalex.org/W1967315849","https://openalex.org/W1992270714","https://openalex.org/W1994389483","https://openalex.org/W2000359198","https://openalex.org/W2054141820","https://openalex.org/W2070786785","https://openalex.org/W2080320419","https://openalex.org/W2098935637","https://openalex.org/W2102705353","https://openalex.org/W2109722477","https://openalex.org/W2110086534","https://openalex.org/W2142715798","https://openalex.org/W2146635036","https://openalex.org/W2166925272","https://openalex.org/W2173213060","https://openalex.org/W2317002898","https://openalex.org/W2341535507","https://openalex.org/W2963215849","https://openalex.org/W6602324189","https://openalex.org/W6635302267","https://openalex.org/W6676367512","https://openalex.org/W6703949738"],"related_works":["https://openalex.org/W1538652242","https://openalex.org/W2011521129","https://openalex.org/W4379164835","https://openalex.org/W2461968736","https://openalex.org/W4386544342","https://openalex.org/W1971438544","https://openalex.org/W2481053450","https://openalex.org/W2034909456","https://openalex.org/W4254487859","https://openalex.org/W2514911858"],"abstract_inverted_index":{"Many":[0],"modern":[1],"enterprises":[2],"are":[3],"collecting":[4],"data":[5,13,32,47,58,71,99,171,182],"at":[6,142],"the":[7,62,96,136,143,160,169,179,224],"most":[8],"detailed":[9],"level":[10],"possible,":[11],"creating":[12],"repositories":[14,48],"ranging":[15],"from":[16,210],"terabytes":[17],"to":[18,24,30,41,53,110,177,193,205,226,237],"petabytes":[19,111],"in":[20,92,123],"size.":[21],"The":[22],"ability":[23],"apply":[25],"sophisticated":[26],"statistical":[27,55,65,162,229],"analysis":[28,44,72,163,218],"methods":[29],"this":[31],"is":[33,133],"becoming":[34],"essential":[35],"for":[36,70,129],"marketplace":[37],"competitiveness.":[38],"This":[39,174],"need":[40,225],"perform":[42],"deep":[43,130],"over":[45],"huge":[46,208],"poses":[49],"a":[50,126,151,212],"significant":[51],"challenge":[52],"existing":[54],"software":[56,66],"and":[57,73,88,148,165,202,216],"management":[59,100,172],"systems.":[60],"On":[61,95],"one":[63,198],"hand,":[64,98],"provides":[67],"rich":[68],"functionality":[69],"modeling,":[74],"but":[75,114],"can":[76,108,234],"handle":[77],"only":[78,197],"limited":[79],"amounts":[80],"of":[81,112,135,153,181,200],"data;":[82],"e.g.,":[83],"popular":[84],"packages":[85],"like":[86],"R":[87,161],"SPSS":[89],"operate":[90],"entirely":[91],"main":[93],"memory.":[94],"other":[97],"systems":[101,106],"-":[102,107],"such":[103],"as":[104],"MapReduce-based":[105],"scale":[109],"data,":[113],"provide":[115],"insufficient":[116],"analytical":[117],"functionality.":[118],"We":[119],"report":[120],"our":[121,221],"experiences":[122],"building":[124],"Ricardo,":[125],"scalable":[127],"platform":[128],"analytics.":[131],"Ricardo":[132,186],"part":[134],"eXtreme":[137],"Analytics":[138],"Platform":[139],"(XAP)":[140],"project":[141],"IBM":[144],"Almaden":[145],"Research":[146],"Center,":[147],"rests":[149],"on":[150,207],"decomposition":[152,175],"data-analysis":[154],"algorithms":[155],"into":[156],"parts":[157,166],"executed":[158],"by":[159,168],"system":[164,184],"handled":[167],"Hadoop":[170],"system.":[173],"attempts":[176],"minimize":[178],"transfer":[180],"across":[183],"boundaries.":[185],"contrasts":[187],"with":[188,196],"previous":[189],"approaches,":[190],"which":[191],"try":[192],"get":[194],"along":[195],"type":[199],"system,":[201],"allows":[203],"analysts":[204],"work":[206],"datasets":[209],"within":[211],"popular,":[213],"well":[214],"supported,":[215],"powerful":[217],"environment.":[219],"Because":[220],"approach":[222],"avoids":[223],"re-implement":[227],"either":[228],"or":[230],"data-management":[231],"functionality,":[232],"it":[233],"be":[235],"used":[236],"solve":[238],"complex":[239],"problems":[240],"right":[241],"now.":[242]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":25},{"year":2013,"cited_by_count":27},{"year":2012,"cited_by_count":14}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}