{"id":"https://openalex.org/W2584412193","doi":"https://doi.org/10.1109/bigdata.2016.7840776","title":"QED: Groupon's ETL management and curated feature catalog system for machine learning","display_name":"QED: Groupon's ETL management and curated feature catalog system for machine learning","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2584412193","doi":"https://doi.org/10.1109/bigdata.2016.7840776","mag":"2584412193"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5074156736","display_name":"Derrick C. Spell","orcid":null},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Derrick C. Spell","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052516404","display_name":"Ling-Yong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling-Yong Wang","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090023688","display_name":"Richard T. Shomer","orcid":null},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard T. Shomer","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016867772","display_name":"Bahador Nooraei","orcid":null},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahador Nooraei","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058298152","display_name":"Jarrell Waggoner","orcid":null},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jarrell Waggoner","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022448564","display_name":"Xiaohan Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao-Han T. Zeng","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019234679","display_name":"Jae Young Chung","orcid":"https://orcid.org/0000-0003-0073-4314"},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jae Young Chung","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064766894","display_name":"Kai-Chen Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai-Chen Cheng","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019704468","display_name":"Daniel Kirsche","orcid":null},"institutions":[{"id":"https://openalex.org/I3200592077","display_name":"Capital Group (United States)","ror":"https://ror.org/00cjvpn28","country_code":"US","type":"company","lineage":["https://openalex.org/I3200592077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Kirsche","raw_affiliation_strings":["Groupon, Inc"],"affiliations":[{"raw_affiliation_string":"Groupon, Inc","institution_ids":["https://openalex.org/I3200592077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5074156736"],"corresponding_institution_ids":["https://openalex.org/I3200592077"],"apc_list":null,"apc_paid":null,"fwci":0.3591,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72788923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1639","last_page":"1646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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":0.9984999895095825,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9973000288009644,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8094910979270935},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.642460286617279},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6049907207489014},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5700099468231201},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4774627983570099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46198922395706177},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4483434855937958},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43410444259643555},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42857086658477783},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.41250890493392944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.399644136428833},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39919668436050415},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34712377190589905},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16416886448860168},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10309174656867981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8094910979270935},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.642460286617279},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6049907207489014},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5700099468231201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4774627983570099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46198922395706177},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4483434855937958},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43410444259643555},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42857086658477783},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.41250890493392944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.399644136428833},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39919668436050415},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34712377190589905},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16416886448860168},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10309174656867981},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"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":11,"referenced_works":["https://openalex.org/W2070600700","https://openalex.org/W2083755493","https://openalex.org/W2130204178","https://openalex.org/W2131975293","https://openalex.org/W2165093166","https://openalex.org/W2186090720","https://openalex.org/W2438792749","https://openalex.org/W2510174253","https://openalex.org/W6631138889","https://openalex.org/W6679182178","https://openalex.org/W6679815717"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"In":[0,59],"today's":[1],"technology":[2],"industry":[3],"where":[4],"machine":[5,77,175,188],"learning":[6,78,176,189],"has":[7],"become":[8],"essential,":[9],"the":[10,49,56,90,137,181,196,201],"effectiveness":[11],"of":[12,35,121,140,152,174,187,204],"algorithms":[13],"ultimately":[14],"depends":[15],"on":[16],"a":[17,123,129,185],"robust":[18],"data":[19,87,98,104,146,182],"pipeline,":[20],"and":[21,25,31,38,52,68,85,106,172,199],"fast":[22,158],"model":[23,46,53],"prototyping":[24],"tuning":[26],"require":[27],"easy":[28],"feature":[29,70,141,167],"discovery":[30],"consumption.":[32],"Careful":[33],"management":[34,67],"ETL":[36,66,95],"processes":[37],"their":[39,108],"produced":[40],"datasets":[41,154],"is":[42,117],"key":[43,193],"to":[44,89,113,161],"both":[45],"development":[47],"in":[48,55,102,111],"research":[50],"stage":[51],"execution":[54],"production":[57,91],"environment.":[58],"this":[60],"paper":[61],"we":[62],"present":[63],"QED,":[64],"an":[65],"curated":[69,166],"catalog":[71,168],"system":[72,169],"that":[73,191],"provides":[74],"robust,":[75],"streamlined":[76],"pipelines.":[79],"First,":[80],"QED":[81,116,178],"promises":[82],"dynamic,":[83],"reliable,":[84],"timely":[86],"delivery":[88],"pipeline.":[92],"Its":[93],"enhanced":[94],"process":[96,151],"persists":[97],"from":[99],"upstream":[100],"sources":[101],"local":[103],"stores":[105],"ensures":[107],"correctness.":[109],"Second,":[110],"contrast":[112],"previous":[114],"systems,":[115],"capable":[118],"not":[119],"only":[120],"producing":[122],"daily":[124,202],"scoring":[125],"dataset,":[126],"but":[127],"also":[128],"training":[130],"dataset":[131],"with":[132],"minimized":[133],"bias":[134],"by":[135],"preserving":[136],"historical":[138],"observations":[139],"values.":[142],"Third,":[143],"QED's":[144],"multiple":[145],"store":[147],"design":[148],"allows":[149],"batch":[150],"large":[153],"as":[155,157,180],"well":[156],"random":[159],"access":[160],"single":[162],"records.":[163],"Finally,":[164],"its":[165],"enables":[170],"sharing":[171],"reuse":[173],"features.":[177],"serves":[179],"backend":[183],"for":[184],"variety":[186],"models":[190],"provide":[192],"insights":[194],"into":[195],"global":[197],"business,":[198],"optimize":[200],"operations":[203],"Groupon.":[205]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}