{"id":"https://openalex.org/W2024002477","doi":"https://doi.org/10.1109/soli.2012.6273508","title":"Automated selection of blocking columns for record linkage","display_name":"Automated selection of blocking columns for record linkage","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2024002477","doi":"https://doi.org/10.1109/soli.2012.6273508","mag":"2024002477"},"language":"en","primary_location":{"id":"doi:10.1109/soli.2012.6273508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/soli.2012.6273508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2012 IEEE International Conference on Service Operations and Logistics, and Informatics","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058758292","display_name":"Kalika Prasad","orcid":"https://orcid.org/0000-0001-8666-856X"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Hima Prasad","raw_affiliation_strings":["IBM Research India, New Delhi, India","IBM Research-India, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Research-India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041254552","display_name":"Snigdha Chaturvedi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Snigdha Chaturvedi","raw_affiliation_strings":["IBM Research India, New Delhi, India","IBM Research-India, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Research-India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004954473","display_name":"Tanveer A. Faruquie","orcid":"https://orcid.org/0009-0008-9474-7928"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanveer A. Faruquie","raw_affiliation_strings":["IBM Research India, New Delhi, India","IBM Research-India, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Research-India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110629023","display_name":"L. Venkata Subramaniam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"L. Venkata Subramaniam","raw_affiliation_strings":["IBM Research India, New Delhi, India","IBM Research-India, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Research-India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mukesh K. Mohania","raw_affiliation_strings":["IBM Research India, New Delhi, India","IBM Research-India, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Research-India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"78","last_page":"83"},"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":0.9351000189781189,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9279999732971191,"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/blocking","display_name":"Blocking (statistics)","score":0.933582067489624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7305197715759277},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.7264491319656372},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6656387448310852},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5583631992340088},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5292260646820068},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5285091996192932},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48640182614326477},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.4720523953437805},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.46730685234069824},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43522346019744873},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28362634778022766},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12252318859100342},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12077248096466064},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11177113652229309},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0897420346736908}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.933582067489624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305197715759277},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.7264491319656372},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6656387448310852},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5583631992340088},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5292260646820068},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5285091996192932},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48640182614326477},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.4720523953437805},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.46730685234069824},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43522346019744873},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28362634778022766},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12252318859100342},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12077248096466064},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11177113652229309},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0897420346736908},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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:10.1109/soli.2012.6273508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/soli.2012.6273508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2012 IEEE International Conference on Service Operations and Logistics, and Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1597164057","https://openalex.org/W1612155886","https://openalex.org/W1647671624","https://openalex.org/W1982723649","https://openalex.org/W1986983672","https://openalex.org/W1995875735","https://openalex.org/W1997927541","https://openalex.org/W2024770506","https://openalex.org/W2034190452","https://openalex.org/W2041404167","https://openalex.org/W2073251771","https://openalex.org/W2099111195","https://openalex.org/W2124379907","https://openalex.org/W2161600801","https://openalex.org/W2171574281","https://openalex.org/W2323834113","https://openalex.org/W2478708596","https://openalex.org/W2993383518","https://openalex.org/W4243310333","https://openalex.org/W4285719527","https://openalex.org/W6636915900","https://openalex.org/W6674851815","https://openalex.org/W6685232391","https://openalex.org/W6771752040"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Record":[0],"Linkage":[1],"is":[2,54,117],"an":[3],"essential":[4],"but":[5],"expensive":[6],"step":[7],"in":[8,195],"enterprise":[9],"data":[10,70,107,114,145,169],"management.":[11],"In":[12,126],"most":[13],"deployments,":[14],"blocking":[15,52,64,91,98,124,137,162,178],"techniques":[16],"are":[17],"employed":[18,194],"which":[19],"can":[20,74,100,202],"reduce":[21],"the":[22,30,34,57,63,85,90,94,104,120,141,164],"number":[23],"of":[24,33,42,50,84,96,106,122,144,154,166,177],"record":[25],"pair":[26],"comparisons":[27],"and":[28,59,66,88,108,171,185],"hence,":[29],"computational":[31],"complexity":[32],"task.":[35],"Blocking":[36],"algorithms":[37],"require":[38],"a":[39,81,131,151],"careful":[40],"selection":[41,95,121],"column(s)":[43,99],"to":[44,56,79,134,192],"be":[45,193,203],"used":[46,204],"for":[47,119,159,161,205],"blocking.":[48,206],"Selection":[49],"appropriate":[51],"column":[53,201],"critical":[55],"accuracy":[58],"speed-up":[60],"offered":[61],"by":[62,69,156],"technique":[65],"requires":[67,109],"intervention":[68],"quality":[71,105,115,146,170],"practitioners":[72],"who":[73],"exploit":[75],"prior":[76],"domain":[77],"knowledge":[78],"analyse":[80],"small":[82],"sample":[83],"huge":[86],"database":[87],"decide":[89],"column(s).":[92],"However,":[93],"optimal":[97,123],"depend":[101],"heavily":[102],"on":[103,163,182],"extensive":[110],"analysis.":[111],"An":[112],"experienced":[113],"practitioner":[116],"required":[118],"columns.":[125],"this":[127],"paper,":[128],"we":[129],"present":[130],"datadriven":[132],"approach":[133,149,191],"automatically":[135],"choose":[136],"column(s),":[138],"motivated":[139],"from":[140],"modus":[142],"operandi":[143],"practitioners.":[147],"Our":[148],"produces":[150],"ranked":[152],"list":[153],"columns":[155,179],"evaluating":[157],"them":[158],"appropriateness":[160],"basis":[165],"factors":[167],"including":[168],"distribution.":[172],"We":[173,188],"evaluate":[174],"our":[175,190],"choice":[176],"through":[180],"experiments":[181],"real":[183],"world":[184],"synthetic":[186],"datasets.":[187],"extend":[189],"scenarios":[196],"where":[197],"more":[198],"than":[199],"one":[200]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}