{"id":"https://openalex.org/W2204201938","doi":"https://doi.org/10.1109/bigdata.2015.7363734","title":"Conquering Big Data with Spark","display_name":"Conquering Big Data with Spark","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2204201938","doi":"https://doi.org/10.1109/bigdata.2015.7363734","mag":"2204201938"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big 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/A5009932781","display_name":"Ion Stocia","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ion Stocia","raw_affiliation_strings":["UC Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009932781"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.14824239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.8876000046730042,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.8876000046730042,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.8080000281333923,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.9398078918457031},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.894183874130249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800197601318359},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6244022250175476},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.6017208695411682},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5094922184944153},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45910122990608215},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.42408353090286255},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.35695064067840576},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3311404585838318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09735405445098877}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.9398078918457031},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.894183874130249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800197601318359},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6244022250175476},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.6017208695411682},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5094922184944153},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45910122990608215},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42408353090286255},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.35695064067840576},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3311404585838318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09735405445098877},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W3191926225","https://openalex.org/W2093907010"],"abstract_inverted_index":{"Today,":[0],"big":[1,62,111],"and":[2,11,26,40,91,102,119],"small":[3],"organizations":[4],"alike":[5],"collect":[6],"huge":[7],"amounts":[8],"of":[9,97],"data,":[10],"they":[12],"do":[13],"so":[14],"with":[15],"one":[16,126],"goal":[17],"in":[18,74,114],"mind:":[19],"extract":[20],"\"value\"":[21],"through":[22],"sophisticated":[23],"exploratory":[24],"analysis,":[25],"use":[27],"it":[28],"as":[29,35,37],"the":[30,71,108,115],"basis":[31],"to":[32],"make":[33],"decisions":[34],"varied":[36],"personalized":[38],"treatment":[39],"ad":[41],"targeting.":[42],"To":[43],"address":[44],"this":[45,66],"challenge,":[46],"we":[47],"have":[48],"developed":[49],"Berkeley":[50],"Data":[51],"Analytics":[52],"Stack":[53],"(BDAS),":[54],"an":[55],"open":[56,116],"source":[57,117],"data":[58,63,112],"analytics":[59],"stack":[60],"for":[61,88,94],"processing.":[64],"In":[65],"talk":[67],"I'll":[68],"focus":[69],"on":[70],"execution":[72],"engine":[73,84],"BDAS:":[75],"Apache":[76,78],"Spark.":[77],"Spark":[79,105],"is":[80,86,106,120],"a":[81,95],"cluster":[82],"computing":[83],"that":[85],"optimized":[87],"in-memory":[89],"processing,":[90],"unifies":[92],"support":[93],"variety":[96],"workloads,":[98],"including":[99],"batch,":[100],"streaming,":[101],"iterative":[103],"computations.":[104],"now":[107],"most":[109],"active":[110],"project":[113],"community,":[118],"already":[121],"being":[122],"used":[123],"by":[124],"over":[125],"thousand":[127],"organizations.":[128]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}