{"id":"https://openalex.org/W3145232008","doi":"https://doi.org/10.1145/3277006.3277015","title":"Technical Perspective:","display_name":"Technical Perspective:","publication_year":2018,"publication_date":"2018-09-10","ids":{"openalex":"https://openalex.org/W3145232008","doi":"https://doi.org/10.1145/3277006.3277015","mag":"3145232008"},"language":"en","primary_location":{"id":"doi:10.1145/3277006.3277015","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3277006.3277015","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-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/A5086134487","display_name":"Pradap Konda","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pradap Konda","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016507428","display_name":"Sanjib Das","orcid":"https://orcid.org/0000-0002-3051-7786"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjib Das","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104217740","display_name":"Paul Suganthan","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Suganthan G.C.","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073422308","display_name":"Philip Martinkus","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Martinkus","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086032713","display_name":"Adel Ardalan","orcid":"https://orcid.org/0000-0001-5061-7832"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adel Ardalan","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026326684","display_name":"Jeffrey R. Ballard","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey R. Ballard","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088781274","display_name":"Yash Govind","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yash Govind","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452631","display_name":"Han Li","orcid":"https://orcid.org/0009-0003-1556-5696"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Li","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001252821","display_name":"Fatemah Panahi","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":"Fatemah Panahi","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101961485","display_name":"Haojun Zhang","orcid":"https://orcid.org/0000-0002-9801-2514"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haojun Zhang","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074213929","display_name":"Jeff Naughton","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":"Jeff Naughton","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036349156","display_name":"Shishir Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shishir Prasad","raw_affiliation_strings":["@WalmartLabs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"@WalmartLabs","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104009018","display_name":"Ganesh Krishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ganesh Krishnan","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084111141","display_name":"Rohit Deep","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Deep","raw_affiliation_strings":["@WalmartLabs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"@WalmartLabs","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010489647","display_name":"Vijay Raghavendra","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Raghavendra","raw_affiliation_strings":["@WalmartLabs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"@WalmartLabs","institution_ids":["https://openalex.org/I1330693074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6369,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75578715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"47","issue":"1","first_page":"33","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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":0.9986000061035156,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.886515736579895},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7963144183158875},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.740147054195404},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5250563621520996},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4786492586135864},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4519576132297516},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4265420436859131},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.40847355127334595},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33251529932022095},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22032296657562256},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1935160756111145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.886515736579895},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7963144183158875},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.740147054195404},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5250563621520996},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4786492586135864},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4519576132297516},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4265420436859131},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40847355127334595},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33251529932022095},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22032296657562256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1935160756111145},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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:10.1145/3277006.3277015","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3277006.3277015","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W31051396","https://openalex.org/W1567056755","https://openalex.org/W1582775886","https://openalex.org/W1728842521","https://openalex.org/W1992896169","https://openalex.org/W2027084300","https://openalex.org/W2031250218","https://openalex.org/W2046298800","https://openalex.org/W2052698082","https://openalex.org/W2067566391","https://openalex.org/W2107966677","https://openalex.org/W2108991785","https://openalex.org/W2119320829","https://openalex.org/W2127058057","https://openalex.org/W2137406659","https://openalex.org/W2139021951","https://openalex.org/W2168144930","https://openalex.org/W2542998387","https://openalex.org/W2546672044","https://openalex.org/W2583531003","https://openalex.org/W2604399864","https://openalex.org/W2612526608","https://openalex.org/W2612732335","https://openalex.org/W2767681556","https://openalex.org/W2786552522","https://openalex.org/W2792196230","https://openalex.org/W2798649495","https://openalex.org/W2810039498","https://openalex.org/W2949612967","https://openalex.org/W3099883947","https://openalex.org/W4242744113","https://openalex.org/W6692551300","https://openalex.org/W6699636551"],"related_works":["https://openalex.org/W3023169329","https://openalex.org/W2782165897","https://openalex.org/W4300438041","https://openalex.org/W2054104202","https://openalex.org/W2139703748","https://openalex.org/W2761254753","https://openalex.org/W2188981919","https://openalex.org/W3084909426","https://openalex.org/W3213706029","https://openalex.org/W2236574726"],"abstract_inverted_index":{"Entity":[0],"matching":[1,19,99],"(EM)":[2],"has":[3],"been":[4],"a":[5,45,120,135],"long-standing":[6],"challenge":[7],"in":[8,54,69,125],"data":[9,113,126],"management.":[10],"Most":[11],"current":[12,39,101],"EM":[13,32,40,49,71,93,102],"works":[14],"focus":[15],"only":[16],"on":[17],"developing":[18],"algorithms.":[20],"We":[21,34,149],"argue":[22],"that":[23,63,157],"far":[24],"more":[25],"efforts":[26],"should":[27],"be":[28],"devoted":[29],"to":[30,67,80,89,118,139],"building":[31],"systems.":[33],"discuss":[35],"the":[36,86,91,110,147,159,162],"limitations":[37],"of":[38,48,123,146,161],"systems,":[41],"then":[42],"describe":[43,150],"Magellan,":[44],"new":[46],"kind":[47],"system.":[50,148],"Magellan":[51,117,133,163],"is":[52],"novel":[53],"four":[55],"important":[56],"aspects.":[57],"(1)":[58],"It":[59,77],"provides":[60,78,134],"how-to":[61],"guides":[62],"tell":[64],"users":[65,82],"what":[66],"do":[68],"each":[70],"scenario,":[72],"step":[73],"by":[74],"step.":[75],"(2)":[76],"tools":[79,87],"help":[81],"execute":[83],"these":[84],"steps;":[85],"seek":[88],"cover":[90],"entire":[92],"pipeline,":[94],"not":[95],"just":[96],"blocking":[97],"and":[98,143,153],"as":[100],"systems":[103],"do.":[104],"(3)":[105],"Tools":[106],"are":[107],"built":[108],"into":[109],"Python":[111],"open-source":[112],"science":[114],"ecosystem,":[115],"allowing":[116],"borrow":[119],"rich":[121],"set":[122],"capabilities":[124],"cleaning,":[127],"IE,":[128],"visualization,":[129],"learning,":[130],"etc.":[131],"(4)":[132],"powerful":[136],"scripting":[137],"environment":[138],"facilitate":[140],"interactive":[141],"experimentation":[142],"quick":[144],"\"patching\"":[145],"research":[151],"challenges":[152],"present":[154],"extensive":[155],"experiments":[156],"show":[158],"promise":[160],"approach.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}