{"id":"https://openalex.org/W2613597870","doi":"https://doi.org/10.1145/3035918.3054782","title":"Data Management Challenges in Production Machine Learning","display_name":"Data Management Challenges in Production Machine Learning","publication_year":2017,"publication_date":"2017-05-09","ids":{"openalex":"https://openalex.org/W2613597870","doi":"https://doi.org/10.1145/3035918.3054782","mag":"2613597870"},"language":"en","primary_location":{"id":"doi:10.1145/3035918.3054782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3035918.3054782","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3054782&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3054782&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010950113","display_name":"Neoklis Polyzotis","orcid":"https://orcid.org/0000-0002-2694-8591"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neoklis Polyzotis","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065950643","display_name":"Sudip Roy","orcid":"https://orcid.org/0000-0002-0535-0531"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudip Roy","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012631773","display_name":"Steven Euijong Whang","orcid":"https://orcid.org/0000-0001-6419-931X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Euijong Whang","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112356991","display_name":"Martin Zinkevich","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Zinkevich","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010950113"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":13.6178,"has_fulltext":true,"cited_by_count":203,"citation_normalized_percentile":{"value":0.99264405,"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":"1723","last_page":"1726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9979000091552734,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7216323018074036},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6061287522315979},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5868054628372192},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5532934069633484},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5501722097396851},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.5019371509552002},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4818071722984314},{"id":"https://openalex.org/keywords/open-research","display_name":"Open research","score":0.41654908657073975},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.40845879912376404},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3252831697463989},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1970432698726654},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1937047243118286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216323018074036},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6061287522315979},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5868054628372192},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5532934069633484},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5501722097396851},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.5019371509552002},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4818071722984314},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.41654908657073975},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.40845879912376404},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3252831697463989},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1970432698726654},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1937047243118286},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3035918.3054782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3035918.3054782","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3054782&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3035918.3054782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3035918.3054782","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3054782&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2613597870.pdf","grobid_xml":"https://content.openalex.org/works/W2613597870.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W346507350","https://openalex.org/W1491318920","https://openalex.org/W1586825695","https://openalex.org/W2046769817","https://openalex.org/W2071989194","https://openalex.org/W2098759488","https://openalex.org/W2103201239","https://openalex.org/W2109426455","https://openalex.org/W2112474496","https://openalex.org/W2125943921","https://openalex.org/W2145234058","https://openalex.org/W2161163216","https://openalex.org/W2257756289","https://openalex.org/W2271840356","https://openalex.org/W2306526421","https://openalex.org/W2438792749","https://openalex.org/W2444650685","https://openalex.org/W2548122763","https://openalex.org/W2560713231","https://openalex.org/W2963707382","https://openalex.org/W6629137921"],"related_works":["https://openalex.org/W1995889332","https://openalex.org/W3104163240","https://openalex.org/W2012531322","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W2490303674","https://openalex.org/W2609066826","https://openalex.org/W2810752900","https://openalex.org/W3008693296","https://openalex.org/W4312283151"],"abstract_inverted_index":{"The":[0,39],"tutorial":[1,43],"discusses":[2],"data-management":[3],"issues":[4,29],"that":[5,65],"arise":[6],"in":[7,15,55],"the":[8,42,56,61],"context":[9],"of":[10,41],"machine":[11],"learning":[12],"pipelines":[13],"deployed":[14],"production.":[16],"Informed":[17],"by":[18,69],"our":[19],"own":[20],"experience":[21],"with":[22],"such":[23],"largescale":[24],"pipelines,":[25],"we":[26],"focus":[27],"on":[28],"related":[30],"to":[31,45,52],"understanding,":[32],"validating,":[33],"cleaning,":[34],"and":[35,59],"enriching":[36],"training":[37],"data.":[38],"goal":[40],"is":[44],"bring":[46],"forth":[47],"these":[48],"issues,":[49],"draw":[50],"connections":[51],"prior":[53,70],"work":[54],"database":[57],"literature,":[58],"outline":[60],"open":[62],"research":[63],"questions":[64],"are":[66],"not":[67],"addressed":[68],"art.":[71]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2025-10-10T00:00:00"}