{"id":"https://openalex.org/W2003536960","doi":"https://doi.org/10.1145/2723372.2742784","title":"Why Big Data Industrial Systems Need Rules and What We Can Do About It","display_name":"Why Big Data Industrial Systems Need Rules and What We Can Do About It","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W2003536960","doi":"https://doi.org/10.1145/2723372.2742784","mag":"2003536960"},"language":"en","primary_location":{"id":"doi:10.1145/2723372.2742784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2742784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of 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/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":true,"raw_author_name":"Paul Suganthan G.C.","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101592963","display_name":"Chong Sun","orcid":"https://orcid.org/0009-0007-4696-8067"},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chong Sun","raw_affiliation_strings":["Uber, San Francisco, CA, USA","Uber, San Francisco, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Uber, San Francisco, CA, USA","institution_ids":["https://openalex.org/I2946016260"]},{"raw_affiliation_string":"Uber, San Francisco, CA, USA#TAB#","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097402986","display_name":"Krishna Gayatri K.","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":"Krishna Gayatri K.","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"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, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072623685","display_name":"Frank Yang","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":"Frank Yang","raw_affiliation_strings":["LinkedIn, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"LinkedIn, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024030198","display_name":"Narasimhan Rampalli","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":"Narasimhan Rampalli","raw_affiliation_strings":["@WalmartLabs, San Bruno, CA, USA"],"affiliations":[{"raw_affiliation_string":"@WalmartLabs, San Bruno, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"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, San Bruno, CA, USA"],"affiliations":[{"raw_affiliation_string":"@WalmartLabs, San Bruno, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049323910","display_name":"Esteban Arcaute","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":"Esteban Arcaute","raw_affiliation_strings":["@WalmartLabs, San Bruno, CA, USA"],"affiliations":[{"raw_affiliation_string":"@WalmartLabs, San Bruno, CA, USA","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/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":"Ganesh Krishnan","raw_affiliation_strings":["@WalmartLabs, San Bruno, CA, USA"],"affiliations":[{"raw_affiliation_string":"@WalmartLabs, San Bruno, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"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, San Bruno, CA, USA"],"affiliations":[{"raw_affiliation_string":"@WalmartLabs, San Bruno, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","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, San Bruno, CA, USA"],"affiliations":[{"raw_affiliation_string":"@WalmartLabs, San Bruno, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110256670","display_name":"AnHai Doan","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":"AnHai Doan","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5104217740"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":5.208,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95208136,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"265","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"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":0.8098081350326538},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7700203657150269},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6497364044189453},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.590182363986969},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.5688981413841248},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5435590147972107},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5168960094451904},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24972018599510193},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19152194261550903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098081350326538},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7700203657150269},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6497364044189453},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.590182363986969},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.5688981413841248},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5435590147972107},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5168960094451904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24972018599510193},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19152194261550903},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2723372.2742784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2742784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W70556423","https://openalex.org/W73128518","https://openalex.org/W95356790","https://openalex.org/W167027492","https://openalex.org/W1499578805","https://openalex.org/W1508480967","https://openalex.org/W1516899372","https://openalex.org/W1578784159","https://openalex.org/W1623342295","https://openalex.org/W1670263352","https://openalex.org/W1870305865","https://openalex.org/W1978394996","https://openalex.org/W1981628148","https://openalex.org/W2025047573","https://openalex.org/W2040348939","https://openalex.org/W2049770245","https://openalex.org/W2073830447","https://openalex.org/W2090645789","https://openalex.org/W2095779006","https://openalex.org/W2106950427","https://openalex.org/W2107391405","https://openalex.org/W2107966677","https://openalex.org/W2111032703","https://openalex.org/W2133991754","https://openalex.org/W2139021951","https://openalex.org/W2139874739","https://openalex.org/W2143349571","https://openalex.org/W2143774383","https://openalex.org/W2144416276","https://openalex.org/W2154642793","https://openalex.org/W2158454296","https://openalex.org/W2160605849","https://openalex.org/W2161642325","https://openalex.org/W2162340487","https://openalex.org/W2164547069","https://openalex.org/W2166776180","https://openalex.org/W2167681385","https://openalex.org/W2408298952","https://openalex.org/W4285719527","https://openalex.org/W6630823011","https://openalex.org/W6639274278","https://openalex.org/W6684151790","https://openalex.org/W6713962710"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"Big":[0,124],"Data":[1,125],"industrial":[2,144],"systems":[3,42,145],"that":[4,75,100],"address":[5,134],"problems":[6],"such":[7,29,114],"as":[8,115],"classification,":[9],"information":[10],"extraction,":[11],"and":[12,55,90,98,117,127],"entity":[13],"matching":[14],"very":[15],"commonly":[16],"use":[17],"hand-crafted":[18],"rules.":[19,30,59],"Today,":[20],"however,":[21],"little":[22],"is":[23,77,119,130],"understood":[24],"about":[25],"the":[26,138],"usage":[27,66],"of":[28,63,81,140,142],"In":[31],"this":[32,36],"paper":[33],"we":[34,73],"explore":[35],"issue.":[37],"We":[38,49,60,92],"discuss":[39,93],"how":[40],"these":[41,102],"differ":[43],"from":[44],"those":[45],"considered":[46],"in":[47,67,84,149],"academia.":[48],"describe":[50],"default":[51],"solutions,":[52],"their":[53],"limitations,":[54],"reasons":[56],"for":[57],"using":[58,109],"show":[61,74],"examples":[62],"extensive":[64],"rule":[65,85,135],"industry.":[68],"Contrary":[69],"to":[70,121,133],"popular":[71],"perceptions,":[72],"there":[76],"a":[78],"rich":[79],"set":[80],"research":[82],"challenges":[83],"generation,":[86],"evaluation,":[87],"execution,":[88],"optimization,":[89],"maintenance.":[91],"ongoing":[94],"work":[95],"at":[96],"WalmartLabs":[97],"UW-Madison":[99],"illustrate":[101],"challenges.":[103],"Our":[104],"main":[105],"conclusions":[106],"are":[107],"(1)":[108],"rules":[110,143],"(together":[111],"with":[112],"techniques":[113],"learning":[116],"crowdsourcing)":[118],"fundamental":[120],"building":[122],"semantics-intensive":[123],"systems,":[126],"(2)":[128],"it":[129],"increasingly":[131],"critical":[132],"management,":[136],"given":[137],"tens":[139],"thousands":[141],"often":[146],"manage":[147],"today":[148],"an":[150],"ad-hoc":[151],"fashion.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}