{"id":"https://openalex.org/W2964805546","doi":"https://doi.org/10.1145/3292500.3332296","title":"Data Integration and Machine Learning","display_name":"Data Integration and Machine Learning","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2964805546","doi":"https://doi.org/10.1145/3292500.3332296","mag":"2964805546"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3332296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3332296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/A5101406351","display_name":"Dong Xin","orcid":"https://orcid.org/0000-0002-1414-9354"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Luna Dong","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002060759","display_name":"Theodoros Rekatsinas","orcid":"https://orcid.org/0000-0001-6148-1854"},"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":"Theodoros Rekatsinas","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":2,"corresponding_author_ids":["https://openalex.org/A5101406351"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.1981,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57567181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3193","last_page":"3194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9962000250816345,"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":0.991100013256073,"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/machine-learning","display_name":"Machine learning","score":0.7910754084587097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598720788955688},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.7120100855827332},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6522394418716431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6191229820251465},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4618382155895233},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.425743043422699},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4193729758262634},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4175836443901062},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4154995381832123},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3832140862941742},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2493676245212555},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12550032138824463},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07746142148971558}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7910754084587097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598720788955688},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.7120100855827332},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6522394418716431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6191229820251465},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4618382155895233},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.425743043422699},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4193729758262634},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4175836443901062},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4154995381832123},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3832140862941742},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2493676245212555},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12550032138824463},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07746142148971558},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3332296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3332296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1497523460","https://openalex.org/W1521736627","https://openalex.org/W1565102206","https://openalex.org/W1981590391","https://openalex.org/W2000809552","https://openalex.org/W2016753842","https://openalex.org/W2041439319","https://openalex.org/W2066806792","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2101848544","https://openalex.org/W2103018059","https://openalex.org/W2107966677","https://openalex.org/W2110411158","https://openalex.org/W2134305421","https://openalex.org/W2137479650","https://openalex.org/W2148524305","https://openalex.org/W2163072729","https://openalex.org/W2250635077","https://openalex.org/W2323506184","https://openalex.org/W2404544029","https://openalex.org/W2437617937","https://openalex.org/W2438792749","https://openalex.org/W2516405782","https://openalex.org/W2548122763","https://openalex.org/W2559655401","https://openalex.org/W2591700809","https://openalex.org/W2604259521","https://openalex.org/W2608353553","https://openalex.org/W2612139288","https://openalex.org/W2612526608","https://openalex.org/W2612964472","https://openalex.org/W2613597870","https://openalex.org/W2613751718","https://openalex.org/W2741252866","https://openalex.org/W2769041395","https://openalex.org/W2798649495","https://openalex.org/W2798980199","https://openalex.org/W2805173585","https://openalex.org/W2883780523","https://openalex.org/W2952557513","https://openalex.org/W2959716049","https://openalex.org/W2962902328","https://openalex.org/W2962982640","https://openalex.org/W2963374550","https://openalex.org/W2964152081","https://openalex.org/W4249682906"],"related_works":["https://openalex.org/W3156072338","https://openalex.org/W4281783369","https://openalex.org/W4327925681","https://openalex.org/W3123501546","https://openalex.org/W2516184622","https://openalex.org/W1592788703","https://openalex.org/W2790914452","https://openalex.org/W2068589268","https://openalex.org/W2896600556","https://openalex.org/W3164394112"],"abstract_inverted_index":{"As":[0],"data":[1,15,28,40,56,79,89,114,122,139],"volume":[2],"and":[3,14,36,65,81,100,120,127,134,141],"variety":[4,33],"have":[5,8],"increased,":[6],"so":[7],"the":[9,30,47,75],"ties":[10],"between":[11,78],"machine":[12,20,50,82,94,109,142],"learning":[13,21,51,110],"integration":[16,41,63,80,90,115,140],"become":[17],"stronger.":[18],"For":[19],"to":[22,116],"be":[23],"effective,":[24],"one":[25],"must":[26],"utilize":[27],"from":[29],"greatest":[31],"possible":[32],"of":[34,62,74],"sources;":[35],"this":[37],"is":[38,52],"why":[39],"plays":[42],"a":[43],"key":[44],"role.":[45],"At":[46],"same":[48],"time":[49],"driving":[53],"automation":[54],"in":[55,59],"integration,":[57],"resulting":[58],"overall":[60],"reduction":[61],"costs":[64],"improved":[66],"accuracy.":[67],"This":[68],"tutorial":[69],"focuses":[70],"on":[71,93,113],"three":[72],"aspects":[73],"synergistic":[76],"relationship":[77],"learning:":[83],"(1)":[84],"we":[85,105,129],"survey":[86],"how":[87,107],"state-of-the-art":[88],"solutions":[91],"rely":[92,112],"learning-based":[95],"approaches":[96],"for":[97,123],"accurate":[98],"results":[99],"effective":[101],"human-in-the-loop":[102],"pipelines,":[103],"(2)":[104],"review":[106],"end-to-end":[108],"applications":[111],"identify":[117],"accurate,":[118],"clean,":[119],"relevant":[121],"their":[124],"analytics":[125],"exercises,":[126],"(3)":[128],"discuss":[130],"open":[131],"research":[132],"challenges":[133],"opportunities":[135],"that":[136],"span":[137],"across":[138],"learning.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}