{"id":"https://openalex.org/W46465114","doi":"https://doi.org/10.29012/jpc.v5i1.628","title":"On Regression-Tree-Based Synthetic Data Methods for Business Data","display_name":"On Regression-Tree-Based Synthetic Data Methods for Business Data","publication_year":2013,"publication_date":"2013-08-01","ids":{"openalex":"https://openalex.org/W46465114","doi":"https://doi.org/10.29012/jpc.v5i1.628","mag":"46465114"},"language":"en","primary_location":{"id":"doi:10.29012/jpc.v5i1.628","doi":"https://doi.org/10.29012/jpc.v5i1.628","is_oa":true,"landing_page_url":"https://doi.org/10.29012/jpc.v5i1.628","pdf_url":"https://journalprivacyconfidentiality.org/index.php/jpc/article/download/628/611","source":{"id":"https://openalex.org/S4210191919","display_name":"Journal of Privacy and Confidentiality","issn_l":"2575-8527","issn":["2575-8527"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","poland-20","russia-white-list-4"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Privacy and Confidentiality","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journalprivacyconfidentiality.org/index.php/jpc/article/download/628/611","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003450797","display_name":"Joo Ho Lee","orcid":"https://orcid.org/0000-0001-7307-7744","observed_orcids":["https://orcid.org/0000-0001-7307-7744"]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Joo Ho Lee","raw_affiliation_strings":["Department of Statistics, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]},{"author_position":"middle","author":{"id":null,"display_name":"In Yong Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"In Yong Kim","raw_affiliation_strings":["Department of Statistics, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042533760","display_name":"Christine M. O\u2019Keefe","orcid":"https://orcid.org/0000-0001-8193-7820","observed_orcids":["https://orcid.org/0000-0001-8193-7820"]},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christine M. O'Keefe","raw_affiliation_strings":["Commonwealth Scientific and Industrial Research Organization (CSIRO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Commonwealth Scientific and Industrial Research Organization (CSIRO","institution_ids":["https://openalex.org/I1292875679"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2605,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55001263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"5","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9984999895095825,"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/T14509","display_name":"demographic modeling and climate adaptation","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synthetic-data","display_name":"synthetic data","score":0.9449999928474426},{"id":"https://openalex.org/keywords/regression-trees","display_name":"regression trees","score":0.640999972820282},{"id":"https://openalex.org/keywords/business-data","display_name":"business data","score":0.734000027179718},{"id":"https://openalex.org/keywords/disclosure-risk","display_name":"disclosure risk","score":0.6190000176429749},{"id":"https://openalex.org/keywords/data-confidentiality","display_name":"data confidentiality","score":0.49000000953674316},{"id":"https://openalex.org/keywords/cart","display_name":"CART","score":0.6700000166893005},{"id":"https://openalex.org/keywords/stopping-criterion","display_name":"stopping rules","score":0.8420000076293945},{"id":"https://openalex.org/keywords/categorical-data","display_name":"categorical data","score":0.6200000047683716},{"id":"https://openalex.org/keywords/skewed-distributions","display_name":"skewed distributions","score":0.7770000100135803},{"id":"https://openalex.org/keywords/exploratory-data-analysis","display_name":"exploratory data analysis","score":0.7860000133514404},{"id":"https://openalex.org/keywords/linear-regression","display_name":"linear regression","score":0.6439999938011169},{"id":"https://openalex.org/keywords/data-synthesis","display_name":"data synthesis","score":0.43299999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035627961158752},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6495790481567383},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6239644289016724},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.575348973274231},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5613822340965271},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5407246947288513},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.5113396048545837},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.510987401008606},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4930677115917206},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4666196405887604},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.44729217886924744},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43612924218177795},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4310440719127655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3440045118331909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25784099102020264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1771899163722992},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.29012/jpc.v5i1.628","doi":"https://doi.org/10.29012/jpc.v5i1.628","is_oa":true,"landing_page_url":"https://doi.org/10.29012/jpc.v5i1.628","pdf_url":"https://journalprivacyconfidentiality.org/index.php/jpc/article/download/628/611","source":{"id":"https://openalex.org/S4210191919","display_name":"Journal of Privacy and Confidentiality","issn_l":"2575-8527","issn":["2575-8527"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","poland-20","russia-white-list-4"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Privacy and Confidentiality","raw_type":"journal-article"},{"id":"pmh:oai:repository.cmu.edu:jpc-1088","doi":null,"is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1088&context=jpc","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Privacy and Confidentiality","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:71c17636bbbc449c9784341c1b6d6570","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/71c17636bbbc449c9784341c1b6d6570","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Journal of Privacy and Confidentiality, Vol 5, Iss 1 (2013)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.29012/jpc.v5i1.628","doi":"https://doi.org/10.29012/jpc.v5i1.628","is_oa":true,"landing_page_url":"https://doi.org/10.29012/jpc.v5i1.628","pdf_url":"https://journalprivacyconfidentiality.org/index.php/jpc/article/download/628/611","source":{"id":"https://openalex.org/S4210191919","display_name":"Journal of Privacy and Confidentiality","issn_l":"2575-8527","issn":["2575-8527"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","poland-20","russia-white-list-4"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Privacy and Confidentiality","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W46465114.pdf","grobid_xml":"https://content.openalex.org/works/W46465114.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W187651740","https://openalex.org/W218152113","https://openalex.org/W1481818147","https://openalex.org/W1491523329","https://openalex.org/W1497859558","https://openalex.org/W1594031697","https://openalex.org/W2001994823","https://openalex.org/W2046683581","https://openalex.org/W2078556058","https://openalex.org/W2079229132","https://openalex.org/W2088431433","https://openalex.org/W2145709897","https://openalex.org/W2159894141","https://openalex.org/W2169076391","https://openalex.org/W2478460150","https://openalex.org/W3013289126","https://openalex.org/W3085162807","https://openalex.org/W4239489793","https://openalex.org/W4297957988","https://openalex.org/W6959699416"],"related_works":["https://openalex.org/W2010009771","https://openalex.org/W6912443955","https://openalex.org/W2088431433","https://openalex.org/W3122094707","https://openalex.org/W7099194735","https://openalex.org/W4409817739","https://openalex.org/W4414185321","https://openalex.org/W197598704","https://openalex.org/W4406063644","https://openalex.org/W3081506223"],"abstract_inverted_index":{"This":[0],"paper":[1,191],"concerns":[2],"the":[3,10,40,45,77,129,142,194,232,238,243,249,280,302],"use":[4,65,134],"of":[5,12,47,72,91,128,149,196,220,231,240,242,251,279,305,328],"synthetic":[6,105,201,223],"data":[7,14,19,31,42,78,106,150,157,172,211,224],"for":[8,154,199,282],"protecting":[9],"confidentiality":[11,268],"business":[13,156,171,202,306],"during":[15],"statistical":[16,36,50,73],"analysis.":[17],"Synthetic":[18],"sets":[20,107],"are":[21,178],"traditionally":[22],"constructed":[23],"by":[24],"replacing":[25],"sensitive":[26],"values":[27],"in":[28,76,318],"a":[29,54,126,206,221],"confidential":[30,41],"set":[32],"with":[33,151,187,235],"draws":[34],"from":[35,68,163],"models":[37,51,287],"estimated":[38],"on":[39,123,255,285],"set.":[43],"Unfortunately,":[44],"process":[46],"generating":[48],"effective":[49],"can":[52],"be":[53,316],"difficult":[55],"and":[56,83,95,166,181,213,271,322],"labour-intensive":[57],"task.":[58,80],"Recently,":[59],"it":[60,258],"has":[61,288],"been":[62],"proposed":[63],"to":[64,104,146,237,266,301,315],"easily-implemented":[66],"methods":[67,198,321],"machine":[69],"learning":[70],"instead":[71],"model":[74],"estimation":[75],"synthesis":[79],"J.":[81],"Drechsler":[82],"J.P.":[84],"Reiter":[85],"(2011)":[86],"have":[87,96,159,174,183],"conducted":[88],"an":[89,138,229],"evaluation":[90,230],"four":[92],"such":[93],"methods,":[94],"found":[97],"that":[98,177,262,292,310],"regression":[99,215],"trees":[100],"could":[101],"give":[102,205,274],"rise":[103],"which":[108,158],"provide":[109],"reliable":[110],"analysis":[111,212,233,241,278,313],"results":[112,216,234,239,281],"as":[113,115],"well":[114],"low":[116],"disclosure":[117],"risks.":[118],"Their":[119],"conclusion":[120,144],"was":[121],"based":[122,284],"simulations":[124],"using":[125],"subset":[127],"2002":[130],"Uganda":[131],"census":[132,165],"public":[133],"file.":[135],"It":[136],"is":[137,259,295,299],"interesting":[139],"question":[140],"whether":[141],"same":[143],"applies":[145],"other":[147],"types":[148],"different":[152,161,252],"characteristics,":[153],"example":[155,208],"quite":[160],"characteristics":[162,304],"population":[164],"survey":[167],"data.":[168,203,245,307],"In":[169,189],"particular,":[170],"generally":[173],"few":[175],"variables":[176],"mostly":[179],"categorical,":[180],"often":[182],"highly":[184],"skewed":[185],"distributions":[186],"outliers.":[188],"this":[190,293],"we":[192],"investigate":[193,248],"applicability":[195],"regression-tree-based":[197,222],"constructing":[200],"We":[204,226,246,308],"detailed":[207],"comparing":[209],"exploratory":[210],"linear":[214],"under":[217],"two":[218],"variants":[219],"approach.":[225],"also":[227],"include":[228],"respect":[236],"original":[244],"further":[247],"impact":[250],"stopping":[253],"criteria":[254],"performance.":[256],"While":[257],"certainly":[260,325],"true":[261],"any":[263],"method":[264],"designed":[265],"protect":[267],"introduces":[269],"error,":[270],"may":[272],"indeed":[273],"misleading":[275],"conclusions,":[276],"our":[277],"synthesisers":[283],"CART":[286],"provided":[289],"some":[290],"evidence":[291],"error":[294],"not":[296],"random":[297],"but":[298],"due":[300],"particular":[303],"conclude":[309],"more":[311],"careful":[312],"needs":[314],"done":[317],"applying":[319],"these":[320],"end":[323],"users":[324],"need":[326],"aware":[327],"possible":[329],"discrepancies.":[330]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}