{"id":"https://openalex.org/W2945172243","doi":"https://doi.org/10.1145/3318464.3386146","title":"The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development","display_name":"The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development","publication_year":2020,"publication_date":"2020-05-29","ids":{"openalex":"https://openalex.org/W2945172243","doi":"https://doi.org/10.1145/3318464.3386146","mag":"2945172243"},"language":"en","primary_location":{"id":"doi:10.1145/3318464.3386146","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3318464.3386146","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3318464.3386146","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3318464.3386146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Micah J. Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Micah J. Smith","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Carles Sala","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carles Sala","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"James Max Kanter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Max Kanter","raw_affiliation_strings":["Feature Labs, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Feature Labs, Boston, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Kalyan Veeramachaneni","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kalyan Veeramachaneni","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":3.1266,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93030771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"785","last_page":"800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9950000047683716,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5238000154495239},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.44290000200271606},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3912000060081482},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.37959998846054077},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.36419999599456787},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.34200000762939453},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.33410000801086426}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7942000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7279000282287598},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3318464.3386146","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3318464.3386146","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3318464.3386146","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.08942","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.08942","pdf_url":"https://arxiv.org/pdf/1905.08942","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3318464.3386146","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3318464.3386146","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3318464.3386146","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7746697352","display_name":null,"funder_award_id":"FA8750-17-2-0126","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2945172243.pdf","grobid_xml":"https://content.openalex.org/works/W2945172243.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1831050183","https://openalex.org/W2102539288","https://openalex.org/W2112204321","https://openalex.org/W2168405694","https://openalex.org/W2182353144","https://openalex.org/W2266823300","https://openalex.org/W2542459869","https://openalex.org/W2547190417","https://openalex.org/W2567296875","https://openalex.org/W2611130659","https://openalex.org/W2613536717","https://openalex.org/W2732547613","https://openalex.org/W2773031903","https://openalex.org/W2783239537","https://openalex.org/W2786827964","https://openalex.org/W2807799957","https://openalex.org/W2948742859","https://openalex.org/W2962746093","https://openalex.org/W2970104062","https://openalex.org/W3022734214","https://openalex.org/W6674385629"],"related_works":[],"abstract_inverted_index":{"As":[0],"machine":[1,16,63,67],"learning":[2,17,64,68],"is":[3],"applied":[4],"more":[5],"widely,":[6],"data":[7,82,103,106,144],"scientists":[8],"often":[9],"struggle":[10],"to":[11,36,129,140],"find":[12],"or":[13],"create":[14,130],"end-to-end":[15,134],"systems":[18],"for":[19,61,81],"specific":[20],"tasks.":[21],"The":[22],"proliferation":[23],"of":[24,31,39,116,143,172,181,190],"libraries":[25],"and":[26,28,65,79,84,105,122,152,168,186],"frameworks":[27],"the":[29,32,37,54,188],"complexity":[30],"tasks":[33,185],"have":[34],"led":[35],"emergence":[38],"\"pipeline":[40],"jungles\"":[41],"-":[42,119],"brittle,":[43],"ad":[44],"hoc":[45],"ML":[46,74,85,97,184],"systems.":[47,70],"To":[48],"address":[49],"these":[50,111,127],"problems,":[51],"we":[52,72,92,176],"introduce":[53,73],"Machine":[55],"Learning":[56],"Bazaar,":[57],"a":[58,76,114,131,141],"new":[59],"framework":[60],"developing":[62],"automated":[66],"software":[69,89],"First,":[71],"primitives,":[75],"unified":[77],"API":[78],"specification":[80],"processing":[83],"components":[86,128],"from":[87],"different":[88],"libraries.":[90],"Next,":[91],"compose":[93],"primitives":[94],"into":[95],"usable":[96],"pipelines,":[98],"abstracting":[99],"away":[100],"glue":[101],"code,":[102],"flow,":[104],"storage.":[107],"We":[108,125,162],"further":[109],"pair":[110],"pipelines":[112,193],"with":[113],"hierarchy":[115],"AutoML":[117,135],"strategies":[118],"Bayesian":[120],"optimization":[121],"bandit":[123],"learning.":[124],"use":[126,166],"general-purpose,":[132],"multi-task,":[133],"system":[136],"that":[137],"provides":[138],"solutions":[139],"variety":[142],"modalities":[145],"(image,":[146],"text,":[147],"graph,":[148],"tabular,":[149],"relational,":[150],"etc.)":[151],"problem":[153],"types":[154],"(classification,":[155],"regression,":[156],"anomaly":[157],"detection,":[158],"graph":[159],"matching,":[160],"etc.).":[161],"demonstrate":[163],"5":[164],"real-world":[165,183],"cases":[167],"2":[169],"case":[170],"studies":[171],"our":[173],"approach.":[174],"Finally,":[175],"present":[177],"an":[178],"evaluation":[179],"suite":[180],"456":[182],"describe":[187],"characteristics":[189],"2.5":[191],"million":[192],"searched":[194],"over":[195],"this":[196],"task":[197],"suite.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-05-29T00:00:00"}