{"id":"https://openalex.org/W2798434712","doi":"https://doi.org/10.1145/3183713.3190664","title":"Structured Streaming","display_name":"Structured Streaming","publication_year":2018,"publication_date":"2018-05-25","ids":{"openalex":"https://openalex.org/W2798434712","doi":"https://doi.org/10.1145/3183713.3190664","mag":"2798434712"},"language":"en","primary_location":{"id":"doi:10.1145/3183713.3190664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3190664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 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/A5073379366","display_name":"Michael Armbrust","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Armbrust","raw_affiliation_strings":["Databricks Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103417248","display_name":"Tathagata Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tathagata Das","raw_affiliation_strings":["Databricks Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033782314","display_name":"Joseph Torres","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Torres","raw_affiliation_strings":["Databricks Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027266428","display_name":"Burak Yavuz","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burak Yavuz","raw_affiliation_strings":["Databricks Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004536254","display_name":"Shixiong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shixiong Zhu","raw_affiliation_strings":["Databricks Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000259060","display_name":"Reynold Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reynold Xin","raw_affiliation_strings":["Databricks Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040035859","display_name":"Ali Ghodsi","orcid":"https://orcid.org/0000-0003-1866-246X"},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Ghodsi","raw_affiliation_strings":["Databricks Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041920173","display_name":"Ion Stoica","orcid":"https://orcid.org/0000-0002-5373-0088"},"institutions":[{"id":"https://openalex.org/I4401726825","display_name":"Databricks (United States)","ror":"https://ror.org/01ynzx943","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726825"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ion Stoica","raw_affiliation_strings":["Databricks Inc., San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks Inc., San Francisco, CA, USA","institution_ids":["https://openalex.org/I4401726825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Databricks &Stanford University, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Databricks &Stanford University, San Francisco, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5073379366"],"corresponding_institution_ids":["https://openalex.org/I4401726825"],"apc_list":null,"apc_paid":null,"fwci":19.706,"has_fulltext":false,"cited_by_count":187,"citation_normalized_percentile":{"value":0.99469449,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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":0.9984999895095825,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9916999936103821,"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/T11106","display_name":"Data Management and Algorithms","score":0.9884999990463257,"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":0.8831578493118286},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8312481641769409},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6478395462036133},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.61687833070755},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5670534372329712},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.5559697151184082},{"id":"https://openalex.org/keywords/real-time-streaming-protocol","display_name":"Real Time Streaming Protocol","score":0.5356034636497498},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5046545267105103},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46892908215522766},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.42908287048339844},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4238499402999878},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38947373628616333},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3528158664703369},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20963838696479797},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.09298726916313171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8831578493118286},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8312481641769409},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6478395462036133},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.61687833070755},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5670534372329712},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.5559697151184082},{"id":"https://openalex.org/C110738861","wikidata":"https://www.wikidata.org/wiki/Q682598","display_name":"Real Time Streaming Protocol","level":3,"score":0.5356034636497498},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5046545267105103},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46892908215522766},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.42908287048339844},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4238499402999878},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38947373628616333},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3528158664703369},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20963838696479797},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.09298726916313171},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3183713.3190664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3190664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W193566757","https://openalex.org/W1976821017","https://openalex.org/W1993892970","https://openalex.org/W2010801412","https://openalex.org/W2025387515","https://openalex.org/W2038412523","https://openalex.org/W2082171780","https://openalex.org/W2115503987","https://openalex.org/W2116476518","https://openalex.org/W2131165411","https://openalex.org/W2131975293","https://openalex.org/W2132851185","https://openalex.org/W2144002928","https://openalex.org/W2244876453","https://openalex.org/W2247317079","https://openalex.org/W2318935314","https://openalex.org/W3098257205"],"related_works":["https://openalex.org/W1989140795","https://openalex.org/W2113327063","https://openalex.org/W1981433684","https://openalex.org/W2077180914","https://openalex.org/W2175563412","https://openalex.org/W2403307847","https://openalex.org/W2975331349","https://openalex.org/W2521218765","https://openalex.org/W4387776140","https://openalex.org/W2622236720"],"abstract_inverted_index":{"With":[0],"the":[1,83,164,177],"ubiquity":[2],"of":[3,89,179,185],"real-time":[4,99],"data,":[5],"organizations":[6],"need":[7],"streaming":[8,29,47,103],"systems":[9],"that":[10,81,101,111],"are":[11],"scalable,":[12],"easy":[13,17],"to":[14,18,79,85,96,139],"use,":[15],"and":[16,106,132,141,158,167],"integrate":[19,102],"into":[20],"business":[21],"applications.":[22],"Structured":[23,41,93,121],"Streaming":[24,42,94,122],"is":[25,59],"a":[26,60,68,87,116],"new":[27],"high-level":[28],"API":[30,63],"in":[31,53,77,119],"Apache":[32,135,142],"Spark":[33,39,127],"based":[34,64],"on":[35,65,175],"our":[36],"experience":[37],"with":[38,104],"Streaming.":[40],"differs":[43],"from":[44,170],"other":[45],"recent":[46],"APIs,":[48],"such":[49,153],"as":[50,154],"Google":[51],"Dataflow,":[52],"two":[54],"main":[55],"ways.":[56],"First,":[57],"it":[58],"purely":[61],"declarative":[62],"automatically":[66],"incrementalizing":[67],"static":[69],"relational":[70],"query":[71],"(expressed":[72],"using":[73],"SQL":[74],"or":[75],"DataFrames),":[76],"contrast":[78],"APIs":[80],"ask":[82],"user":[84],"build":[86],"DAG":[88],"physical":[90],"operators.":[91],"Second,":[92],"aims":[95],"support":[97],"end-to-end":[98],"applications":[100],"batch":[105],"interactive":[107],"analysis.":[108],"We":[109,162],"found":[110],"this":[112],"integration":[113],"was":[114],"often":[115],"key":[117],"challenge":[118],"practice.":[120],"achieves":[123],"high":[124],"performance":[125],"via":[126],"SQL's":[128],"code":[129,156],"generation":[130],"engine":[131],"can":[133],"outperform":[134],"Flink":[136],"by":[137,145],"up":[138],"2x":[140],"Kafka":[143],"Streams":[144],"90x.":[146],"It":[147],"also":[148],"offers":[149],"rich":[150],"operational":[151],"features":[152],"rollbacks,":[155],"updates,":[157],"mixed":[159],"streaming/batch":[160],"execution.":[161],"describe":[163],"system's":[165],"design":[166],"use":[168],"cases":[169],"several":[171],"hundred":[172],"production":[173],"deployments":[174],"Databricks,":[176],"largest":[178],"which":[180],"process":[181],"over":[182],"1":[183],"PB":[184],"data":[186],"per":[187],"month.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":5}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}