{"id":"https://openalex.org/W2201152173","doi":"https://doi.org/10.1109/bigdata.2015.7364058","title":"A memory capacity model for high performing data-filtering applications in Samza framework","display_name":"A memory capacity model for high performing data-filtering applications in Samza framework","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2201152173","doi":"https://doi.org/10.1109/bigdata.2015.7364058","mag":"2201152173"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7364058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364058","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/A5049623145","display_name":"Tao Feng","orcid":"https://orcid.org/0000-0002-3276-6129"},"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":"Tao Feng","raw_affiliation_strings":["Linkedln Corp, CA, USA"],"affiliations":[{"raw_affiliation_string":"Linkedln Corp, CA, USA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111922232","display_name":"Zhenyun Zhuang","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":"Zhenyun Zhuang","raw_affiliation_strings":["Linkedln Corp, CA, USA"],"affiliations":[{"raw_affiliation_string":"Linkedln Corp, CA, USA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103252393","display_name":"Yi Pan","orcid":"https://orcid.org/0009-0006-6030-5860"},"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":"Yi Pan","raw_affiliation_strings":["Linkedln Corp, CA, USA"],"affiliations":[{"raw_affiliation_string":"Linkedln Corp, CA, USA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010047053","display_name":"Haricharan Ramachandra","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":"Haricharan Ramachandra","raw_affiliation_strings":["Linkedln Corp, CA, USA"],"affiliations":[{"raw_affiliation_string":"Linkedln Corp, CA, USA","institution_ids":["https://openalex.org/I1316064682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049623145"],"corresponding_institution_ids":["https://openalex.org/I1316064682"],"apc_list":null,"apc_paid":null,"fwci":2.0031,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8798012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2600","last_page":"2605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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":0.9933000206947327,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8251757621765137},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6882699728012085},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.663972020149231},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5057225227355957},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4665166139602661},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4660989046096802},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4427388608455658},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4388897120952606},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41455116868019104},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.37071919441223145},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36736536026000977},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3214358985424042},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24134182929992676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22691547870635986},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13850948214530945},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.0898861289024353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251757621765137},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6882699728012085},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.663972020149231},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5057225227355957},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4665166139602661},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4660989046096802},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4427388608455658},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4388897120952606},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41455116868019104},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37071919441223145},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36736536026000977},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3214358985424042},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24134182929992676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22691547870635986},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13850948214530945},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.0898861289024353},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7364058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364058","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1981001739","https://openalex.org/W1989985775","https://openalex.org/W2049107679","https://openalex.org/W2060417707","https://openalex.org/W2068376489","https://openalex.org/W2081974606","https://openalex.org/W2119745055","https://openalex.org/W2137479650","https://openalex.org/W2153972927","https://openalex.org/W2913854892"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W2891888580","https://openalex.org/W2215544391","https://openalex.org/W4210350690","https://openalex.org/W3081133439","https://openalex.org/W4386246791","https://openalex.org/W2945537679","https://openalex.org/W3211701140","https://openalex.org/W2952280724","https://openalex.org/W2133103607"],"abstract_inverted_index":{"Data":[0],"quality":[1],"is":[2,24,37,61],"essential":[3],"in":[4,45,96,151,168],"big":[5,53],"data":[6,10,29,43,54,66,82],"paradigm":[7],"as":[8],"poor":[9,28,65],"can":[11,122],"have":[12],"serious":[13],"consequences":[14],"when":[15],"dealing":[16],"with":[17],"large":[18],"volumes":[19],"of":[20,58,89,112],"data.":[21],"While":[22],"it":[23,36],"trivial":[25],"to":[26,39,79,108,125,130],"spot":[27],"for":[30,105],"small-scale":[31],"and":[32,41,47,63,92,159],"offline":[33],"use":[34,149],"cases,":[35],"challenging":[38],"detect":[40],"fix":[42],"inconsistency":[44],"large-scale":[46],"online":[48],"(real-time":[49],"or":[50],"near-real":[51],"time)":[52],"context.":[55],"An":[56],"example":[57],"such":[59],"scenario":[60],"spotting":[62],"fixing":[64],"using":[67],"Apache":[68,106],"Samza,":[69],"a":[70,101],"stream":[71],"processing":[72,91],"framework":[73],"that":[74],"has":[75],"been":[76],"increasingly":[77],"adopted":[78],"process":[80],"near-real-time":[81],"at":[83],"LinkedIn.":[84],"To":[85],"optimize":[86],"the":[87,134,137,156],"deployment":[88,157],"Samza":[90,107],"reduce":[93],"business":[94,161],"cost,":[95],"this":[97,169],"work":[98],"we":[99],"propose":[100],"memory":[102,128,138,143],"capacity":[103,144],"model":[104,121,145],"allow":[109],"denser":[110],"deployments":[111],"high":[113],"performing":[114],"data-filtering":[115],"applications":[116,131],"built":[117],"on":[118,136,146],"Samza.":[119],"The":[120],"be":[123],"used":[124],"provision":[126],"just-enough":[127],"resource":[129],"by":[132],"tightening":[133],"bounds":[135],"allocations.":[139],"We":[140,163],"apply":[141],"our":[142],"Linkedln's":[147],"real":[148],"cases":[150],"production,":[152],"which":[153],"significantly":[154],"increases":[155],"density":[158],"saves":[160],"costs.":[162],"will":[164],"share":[165],"key":[166],"learning":[167],"paper.":[170]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}