{"id":"https://openalex.org/W2006801410","doi":"https://doi.org/10.1145/2463676.2463707","title":"The big data ecosystem at LinkedIn","display_name":"The big data ecosystem at LinkedIn","publication_year":2013,"publication_date":"2013-06-22","ids":{"openalex":"https://openalex.org/W2006801410","doi":"https://doi.org/10.1145/2463676.2463707","mag":"2006801410"},"language":"en","primary_location":{"id":"doi:10.1145/2463676.2463707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2463707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 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/A5019111856","display_name":"Roshan Sumbaly","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Roshan Sumbaly","raw_affiliation_strings":["LinkedIn, Mountain View, CA, USA","[LinkedIn, Mountain View, CA, USA]"],"affiliations":[{"raw_affiliation_string":"LinkedIn, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1316064682"]},{"raw_affiliation_string":"[LinkedIn, Mountain View, CA, USA]","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045206229","display_name":"Jay Kreps","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Kreps","raw_affiliation_strings":["LinkedIn, Mountain View, CA, USA","[LinkedIn, Mountain View, CA, USA]"],"affiliations":[{"raw_affiliation_string":"LinkedIn, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1316064682"]},{"raw_affiliation_string":"[LinkedIn, Mountain View, CA, USA]","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017622114","display_name":"Sam Shah","orcid":"https://orcid.org/0000-0002-7743-8479"},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Shah","raw_affiliation_strings":["LinkedIn, Mountain View, CA, USA","[LinkedIn, Mountain View, CA, USA]"],"affiliations":[{"raw_affiliation_string":"LinkedIn, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1316064682"]},{"raw_affiliation_string":"[LinkedIn, Mountain View, CA, USA]","institution_ids":["https://openalex.org/I1316064682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019111856"],"corresponding_institution_ids":["https://openalex.org/I1316064682"],"apc_list":null,"apc_paid":null,"fwci":24.2249,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.99519788,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1125","last_page":"1134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9984999895095825,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9984999895095825,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9973999857902527,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9968000054359436,"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":0.7746627926826477},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6129016876220703},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6068711876869202},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5629117488861084},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5410205125808716},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5185437798500061},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48616692423820496},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4276408553123474},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2937172055244446},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16305306553840637},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1259041428565979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746627926826477},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6129016876220703},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6068711876869202},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5629117488861084},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5410205125808716},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5185437798500061},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48616692423820496},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4276408553123474},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2937172055244446},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16305306553840637},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1259041428565979},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2463676.2463707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2463707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W73088495","https://openalex.org/W188726702","https://openalex.org/W192446467","https://openalex.org/W603723648","https://openalex.org/W1598064945","https://openalex.org/W1854079585","https://openalex.org/W1981420413","https://openalex.org/W1985419898","https://openalex.org/W1993892970","https://openalex.org/W2010879210","https://openalex.org/W2020283709","https://openalex.org/W2027887579","https://openalex.org/W2029237784","https://openalex.org/W2038879656","https://openalex.org/W2040367556","https://openalex.org/W2043924951","https://openalex.org/W2044102377","https://openalex.org/W2073540046","https://openalex.org/W2098931293","https://openalex.org/W2098935637","https://openalex.org/W2108347533","https://openalex.org/W2119528150","https://openalex.org/W2119738171","https://openalex.org/W2124142520","https://openalex.org/W2141862445","https://openalex.org/W2153522563","https://openalex.org/W2153704625","https://openalex.org/W2159094788","https://openalex.org/W2159115664","https://openalex.org/W2166559705","https://openalex.org/W2173213060","https://openalex.org/W2399650993","https://openalex.org/W2420733993","https://openalex.org/W2624304035","https://openalex.org/W3149110965","https://openalex.org/W4249823756","https://openalex.org/W6618549861"],"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":{"The":[0],"use":[1],"of":[2,14,54,92,131],"large-scale":[3],"data":[4,38,110,124],"mining":[5],"and":[6,24,26,40,47,78,83],"machine":[7,41],"learning":[8,42],"has":[9],"proliferated":[10],"through":[11],"the":[12,63,113,129],"adoption":[13],"technologies":[15],"such":[16],"as":[17,86],"Hadoop,":[18],"with":[19],"its":[20],"simple":[21],"programming":[22],"semantics":[23],"rich":[25,70],"active":[27],"ecosystem.":[28,72],"This":[29,73],"paper":[30],"presents":[31],"LinkedIn's":[32],"Hadoop-based":[33],"analytics":[34],"stack,":[35],"which":[36],"allows":[37],"scientists":[39],"researchers":[43],"to":[44,62,80,128,145,151,155,158],"extract":[45],"insights":[46],"build":[48],"product":[49],"features":[50],"from":[51,77,105,149],"massive":[52],"amounts":[53],"data.":[55],"In":[56],"particular,":[57],"we":[58],"present":[59,136],"our":[60,93,163],"solutions":[61],"``last":[64],"mile''":[65],"issues":[66],"in":[67],"providing":[68],"a":[69,118,123],"developer":[71],"includes":[74],"easy":[75],"ingress":[76],"egress":[79],"online":[81,114],"systems,":[82],"managing":[84],"workflows":[85],"production":[87],"processes.":[88],"A":[89],"key":[90],"characteristic":[91],"solution":[94],"is":[95,116,143],"that":[96,122],"these":[97],"distributed":[98],"system":[99,115],"concerns":[100],"are":[101],"completely":[102],"abstracted":[103],"away":[104],"researchers.":[106],"For":[107],"example,":[108],"deploying":[109],"back":[111],"into":[112],"simply":[117],"1-line":[119],"Pig":[120],"command":[121],"scientist":[125],"can":[126],"add":[127],"end":[130],"their":[132],"script.":[133],"We":[134],"also":[135],"case":[137],"studies":[138],"on":[139],"how":[140],"this":[141],"ecosystem":[142],"used":[144],"solve":[146],"problems":[147],"ranging":[148],"recommendations":[150],"news":[152],"feed":[153],"updates":[154],"email":[156],"digesting":[157],"descriptive":[159],"analytical":[160],"dashboards":[161],"for":[162],"members.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}