{"id":"https://openalex.org/W2115662668","doi":"https://doi.org/10.1142/s0219622015500108","title":"Deterministic Linkage as a Preceding Filter for Other Record Linkage Methods","display_name":"Deterministic Linkage as a Preceding Filter for Other Record Linkage Methods","publication_year":2015,"publication_date":"2015-02-18","ids":{"openalex":"https://openalex.org/W2115662668","doi":"https://doi.org/10.1142/s0219622015500108","mag":"2115662668"},"language":"en","primary_location":{"id":"doi:10.1142/s0219622015500108","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219622015500108","pdf_url":null,"source":{"id":"https://openalex.org/S207089700","display_name":"International Journal of Information Technology & Decision Making","issn_l":"0219-6220","issn":["0219-6220","1793-6845"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology &amp; Decision Making","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/A5021788298","display_name":"Murat Sariyar","orcid":"https://orcid.org/0000-0002-5595-689X"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]},{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]},{"id":"https://openalex.org/I7877124","display_name":"Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/001w7jn25","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. Sariyar","raw_affiliation_strings":["Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Center of the Johannes Gutenberg University Mainz, Germany","Institute of Pathology, Charite \u2013 University Medicine Berlin, 12200 Berlin, Germany","TMF \u2013 Technologie- und Methodenplattform e. V., Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Center of the Johannes Gutenberg University Mainz, Germany","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]},{"raw_affiliation_string":"Institute of Pathology, Charite \u2013 University Medicine Berlin, 12200 Berlin, Germany","institution_ids":["https://openalex.org/I7877124"]},{"raw_affiliation_string":"TMF \u2013 Technologie- und Methodenplattform e. V., Berlin, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014815043","display_name":"Andreas Borg","orcid":null},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]},{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Borg","raw_affiliation_strings":["Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Center of the Johannes Gutenberg University Mainz, Germany","Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Center of the Johannes Gutenberg-University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Center of the Johannes Gutenberg University Mainz, Germany","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]},{"raw_affiliation_string":"Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Center of the Johannes Gutenberg-University, Mainz, Germany","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4117,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70713992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"14","issue":"03","first_page":"521","last_page":"533"},"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9178000092506409,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.8184640407562256},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7837308645248413},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.578425407409668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5580974221229553},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4842061996459961},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.463828444480896},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.43298614025115967},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.41069096326828003},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3637462258338928},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34542369842529297},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33024126291275024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32047605514526367},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0882033109664917},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08471783995628357}],"concepts":[{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.8184640407562256},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7837308645248413},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.578425407409668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5580974221229553},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4842061996459961},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.463828444480896},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.43298614025115967},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.41069096326828003},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3637462258338928},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34542369842529297},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33024126291275024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32047605514526367},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0882033109664917},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08471783995628357},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1142/s0219622015500108","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219622015500108","pdf_url":null,"source":{"id":"https://openalex.org/S207089700","display_name":"International Journal of Information Technology & Decision Making","issn_l":"0219-6220","issn":["0219-6220","1793-6845"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology &amp; Decision Making","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:wsi:ijitdm:v:14:y:2015:i:03:n:s0219622015500108","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0219622015500108","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:RePEc:wsi:ijitdm:v:14:y:2015:i:03:p:521-533","is_oa":false,"landing_page_url":"http://www.worldscinet.com/cgi-bin/details.cgi?type=html&amp;id=pii:S0219622015500108","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W41404523","https://openalex.org/W1547556487","https://openalex.org/W1566255553","https://openalex.org/W1964584862","https://openalex.org/W1982806687","https://openalex.org/W2010954655","https://openalex.org/W2024018837","https://openalex.org/W2024428474","https://openalex.org/W2031250218","https://openalex.org/W2065199439","https://openalex.org/W2067566391","https://openalex.org/W2072510577","https://openalex.org/W2073471108","https://openalex.org/W2094423759","https://openalex.org/W2102017163","https://openalex.org/W2123561513","https://openalex.org/W2126275630","https://openalex.org/W2142023452","https://openalex.org/W2147845824","https://openalex.org/W2161284528","https://openalex.org/W2165905100","https://openalex.org/W2170902582","https://openalex.org/W2196576352","https://openalex.org/W2209632033","https://openalex.org/W2794286494","https://openalex.org/W2796623698","https://openalex.org/W2798146545","https://openalex.org/W2912934387","https://openalex.org/W3146259567","https://openalex.org/W4212883601"],"related_works":["https://openalex.org/W2784199898","https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W2176311362","https://openalex.org/W1501601012","https://openalex.org/W3088855600","https://openalex.org/W2024018837","https://openalex.org/W3012491082","https://openalex.org/W3211905090"],"abstract_inverted_index":{"Deterministic":[0],"record":[1],"linkage":[2,24,27,37,120,154],"(RL)":[3],"is":[4,46,63,181],"frequently":[5],"regarded":[6],"as":[7,39,48,59,121],"a":[8,34,40,43,122,135,167],"rival":[9],"to":[10,106,126,130,183],"more":[11],"sophisticated":[12],"strategies":[13],"like":[14],"probabilistic":[15,68,148,190],"RL.":[16,191],"We":[17,95],"investigate":[18],"the":[19,73,108,111,131,156,173],"effect":[20],"of":[21,53,110,118,133,176],"combining":[22],"deterministic":[23,36,119,153,163],"with":[25,66,77],"other":[26],"techniques.":[28],"For":[29],"this":[30,185],"task,":[31],"we":[32],"use":[33],"simple":[35],"strategy":[38,62],"preceding":[41,123],"filter:":[42],"data":[44,93,102,105,146,177],"pair":[45],"classified":[47],"\u2018match'":[49],"if":[50],"all":[51,115,145],"values":[52],"attributes":[54],"considered":[55],"agree":[56],"exactly,":[57],"otherwise":[58],"\u2018nonmatch'.":[60],"This":[61],"separately":[64],"combined":[65],"two":[67,78,91],"RL":[69,149],"methods":[70,81],"based":[71],"on":[72,90],"Fellegi\u2013Sunter":[74],"model":[75],"and":[76,83,103,137],"classification":[79,139],"tree":[80],"(CART":[82],"Bagging).":[84],"An":[85],"empirical":[86],"comparison":[87],"was":[88],"conducted":[89],"real":[92],"sets.":[94],"used":[96],"four":[97],"different":[98],"partitions":[99],"into":[100,186],"training":[101],"test":[104],"increase":[107],"validity":[109],"results.":[112,143],"In":[113],"almost":[114],"cases,":[116,172],"application":[117],"filter":[124],"leads":[125],"better":[127],"results":[128],"compared":[129],"omission":[132],"such":[134],"pre-filter,":[136],"overall":[138],"trees":[140],"exhibited":[141],"best":[142],"On":[144],"sets,":[147],"only":[150],"profited":[151],"from":[152],"when":[155],"underlying":[157,174],"probabilities":[158],"were":[159],"estimated":[160],"before":[161],"applying":[162],"linkage.":[164],"When":[165],"using":[166],"pre-filter":[168],"for":[169,188],"subtracting":[170],"definite":[171],"population":[175],"pairs":[178],"changes.":[179],"It":[180],"crucial":[182],"take":[184],"account":[187],"model-based":[189]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
