{"id":"https://openalex.org/W2512680752","doi":"https://doi.org/10.1145/2905055.2905063","title":"Study and Implementation of Record De-duplication Algorithms","display_name":"Study and Implementation of Record De-duplication Algorithms","publication_year":2016,"publication_date":"2016-03-04","ids":{"openalex":"https://openalex.org/W2512680752","doi":"https://doi.org/10.1145/2905055.2905063","mag":"2512680752"},"language":"en","primary_location":{"id":"doi:10.1145/2905055.2905063","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2905055.2905063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies","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/A5053901660","display_name":"Vaishali Wangikar","orcid":"https://orcid.org/0000-0002-2276-0313"},"institutions":[{"id":"https://openalex.org/I4387152970","display_name":"MIT Academy of Engineering","ror":"https://ror.org/05sjf8653","country_code":null,"type":"education","lineage":["https://openalex.org/I4387152970"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Vaishali Wangikar","raw_affiliation_strings":["MIT Academy of Engineering, Department of Computer Engineering, Pune"],"affiliations":[{"raw_affiliation_string":"MIT Academy of Engineering, Department of Computer Engineering, Pune","institution_ids":["https://openalex.org/I4387152970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089625193","display_name":"Sachin N. Deshmukh","orcid":"https://orcid.org/0000-0002-1212-3118"},"institutions":[{"id":"https://openalex.org/I165259314","display_name":"Dr. Babasaheb Ambedkar Marathwada University","ror":"https://ror.org/033pfj584","country_code":"IN","type":"education","lineage":["https://openalex.org/I165259314"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sachin Deshmukh","raw_affiliation_strings":["Dr. Babasaheb Ambedkar Marathwada University, Department of CSIT, Aurangabad"],"affiliations":[{"raw_affiliation_string":"Dr. Babasaheb Ambedkar Marathwada University, Department of CSIT, Aurangabad","institution_ids":["https://openalex.org/I165259314"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015262706","display_name":"Sunil Bhirud","orcid":"https://orcid.org/0000-0003-2521-6433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunil Bhirud","raw_affiliation_strings":["Department of Computer Engineering and Information Technology, Veermata Jijabai Technological Institute, Mumbai"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Information Technology, Veermata Jijabai Technological Institute, Mumbai","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053901660"],"corresponding_institution_ids":["https://openalex.org/I4387152970"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.10573701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9782000184059143,"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/record-linkage","display_name":"Record linkage","score":0.8007895946502686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7467955946922302},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.730945348739624},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.684369683265686},{"id":"https://openalex.org/keywords/gene-duplication","display_name":"Gene duplication","score":0.6796196699142456},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5651171207427979},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47998306155204773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47618237137794495},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3069819509983063},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07134521007537842},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0636712908744812}],"concepts":[{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.8007895946502686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467955946922302},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.730945348739624},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.684369683265686},{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.6796196699142456},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5651171207427979},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47998306155204773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47618237137794495},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3069819509983063},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07134521007537842},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0636712908744812},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2905055.2905063","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2905055.2905063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1610496399","https://openalex.org/W1612155886","https://openalex.org/W1997927541","https://openalex.org/W2024770506","https://openalex.org/W2027393969","https://openalex.org/W2031250218","https://openalex.org/W2032552117","https://openalex.org/W2035615211","https://openalex.org/W2036216970","https://openalex.org/W2058733945","https://openalex.org/W2077044633","https://openalex.org/W2108991785","https://openalex.org/W2112912553","https://openalex.org/W2117974736","https://openalex.org/W2140688797","https://openalex.org/W2150228342","https://openalex.org/W2166988329","https://openalex.org/W3146259567","https://openalex.org/W4254422375","https://openalex.org/W6636177537"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W2794928845","https://openalex.org/W2769740009","https://openalex.org/W2031250218","https://openalex.org/W3111311671","https://openalex.org/W3134742116"],"abstract_inverted_index":{"Record":[0],"de-duplication":[1,35,80],"is":[2,24,39,43,58],"a":[3,16,91],"process":[4],"of":[5,9,90,98],"identification":[6],"and":[7,36,81,94],"removal":[8],"duplicates":[10,47,62],"from":[11,52,67],"the":[12,28,31,41,46,56,61,74,78,96],"given":[13],"dataset":[14,54],"in":[15,27,103],"data":[17,87,92,99],"warehouse":[18,93],"environment.":[19],"The":[20],"term":[21],"record":[22,34,37,82],"linkage":[23,38,83],"also":[25],"used":[26,44,59],"same":[29,75],"context,":[30],"difference":[32],"between":[33],"that":[40,71],"former":[42],"when":[45,60],"are":[48,63,84],"to":[49,64,73,106],"be":[50,65],"removed":[51,66],"one":[53],"while":[55],"later":[57],"several":[68],"different":[69],"datasets":[70],"refer":[72],"entity.":[76],"Both":[77],"processes":[79],"important":[85],"during":[86],"profiling":[88],"stage":[89],"assure":[95],"quality":[97],"without":[100],"repetition":[101],"which":[102],"turn":[104],"leads":[105],"better":[107],"decision":[108],"making.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
