{"id":"https://openalex.org/W4320024210","doi":"https://doi.org/10.1109/bigdata55660.2022.10021001","title":"GenSyn: A Multi-stage Framework for Generating Synthetic Microdata using Macro Data Sources","display_name":"GenSyn: A Multi-stage Framework for Generating Synthetic Microdata using Macro Data Sources","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024210","doi":"https://doi.org/10.1109/bigdata55660.2022.10021001"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10021001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10021001","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5076135660","display_name":"Angeela Acharya","orcid":"https://orcid.org/0000-0002-3138-4129"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Angeela Acharya","raw_affiliation_strings":["George Mason University,Fairfax,Virginia,USA","George Mason University, Fairfax, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University,Fairfax,Virginia,USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, Fairfax, Virginia, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075067189","display_name":"Siddhartha Sikdar","orcid":"https://orcid.org/0000-0002-6426-2320"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Sikdar","raw_affiliation_strings":["George Mason University,Fairfax,Virginia,USA","George Mason University, Fairfax, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University,Fairfax,Virginia,USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, Fairfax, Virginia, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046273513","display_name":"Sanmay Das","orcid":"https://orcid.org/0000-0002-6814-871X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanmay Das","raw_affiliation_strings":["George Mason University,Fairfax,Virginia,USA","George Mason University, Fairfax, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University,Fairfax,Virginia,USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, Fairfax, Virginia, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006915473","display_name":"Huzefa Rangwala","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huzefa Rangwala","raw_affiliation_strings":["George Mason University,Fairfax,Virginia,USA","George Mason University, Fairfax, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University,Fairfax,Virginia,USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, Fairfax, Virginia, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076135660"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.5148,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.620782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"685","last_page":"692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14509","display_name":"demographic modeling and climate adaptation","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/T14509","display_name":"demographic modeling and climate adaptation","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/T12011","display_name":"Insurance, Mortality, Demography, Risk Management","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/3317","display_name":"Demography"},"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/T10235","display_name":"Health disparities and outcomes","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.757750391960144},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6294312477111816},{"id":"https://openalex.org/keywords/microdata","display_name":"Microdata (statistics)","score":0.623211145401001},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5953071713447571},{"id":"https://openalex.org/keywords/univariate","display_name":"Univariate","score":0.5303770899772644},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5126394629478455},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.4667613208293915},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.44636934995651245},{"id":"https://openalex.org/keywords/copula","display_name":"Copula (linguistics)","score":0.44293534755706787},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.40405407547950745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3169049918651581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25060462951660156},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.19406694173812866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12266993522644043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757750391960144},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6294312477111816},{"id":"https://openalex.org/C2778355071","wikidata":"https://www.wikidata.org/wiki/Q1933849","display_name":"Microdata (statistics)","level":4,"score":0.623211145401001},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5953071713447571},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.5303770899772644},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5126394629478455},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.4667613208293915},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.44636934995651245},{"id":"https://openalex.org/C17618745","wikidata":"https://www.wikidata.org/wiki/Q207509","display_name":"Copula (linguistics)","level":2,"score":0.44293534755706787},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.40405407547950745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3169049918651581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25060462951660156},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.19406694173812866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12266993522644043},{"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},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C52130261","wikidata":"https://www.wikidata.org/wiki/Q39825","display_name":"Census","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10021001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10021001","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W92899982","https://openalex.org/W105785986","https://openalex.org/W1981806743","https://openalex.org/W2021887957","https://openalex.org/W2050249319","https://openalex.org/W2062925734","https://openalex.org/W2107521066","https://openalex.org/W2111612236","https://openalex.org/W2130690138","https://openalex.org/W2131412630","https://openalex.org/W2152180600","https://openalex.org/W2158963070","https://openalex.org/W2280339326","https://openalex.org/W2480108005","https://openalex.org/W2786532017","https://openalex.org/W3047284506","https://openalex.org/W3096061161","https://openalex.org/W3129829742","https://openalex.org/W4300928835","https://openalex.org/W4312541799","https://openalex.org/W4320013936","https://openalex.org/W6620413488","https://openalex.org/W6789679389","https://openalex.org/W6793947283","https://openalex.org/W6931416441"],"related_works":["https://openalex.org/W3124882577","https://openalex.org/W2045945431","https://openalex.org/W3121353175","https://openalex.org/W2035955891","https://openalex.org/W4298259670","https://openalex.org/W3123218450","https://openalex.org/W3144851602","https://openalex.org/W1828158523","https://openalex.org/W4220747348","https://openalex.org/W4390603992"],"abstract_inverted_index":{"Individual-level":[0],"data":[1,17,34,44,53,61,160],"(microdata)":[2],"that":[3,69,146],"characterizes":[4],"a":[5,47,67,71,80,110,124],"population,":[6],"is":[7,18,29],"essential":[8],"for":[9,98],"studying":[10],"many":[11],"real-world":[12,142],"problems.":[13],"However,":[14],"acquiring":[15],"such":[16],"not":[19],"straightforward":[20],"due":[21],"to":[22,32,49,94,127],"cost":[23],"and":[24,27,75,113,144],"privacy":[25],"constraints,":[26],"access":[28],"often":[30],"limited":[31],"aggregated":[33],"(macro":[35],"data)":[36],"sources.":[37,62],"In":[38,63],"this":[39],"study,":[40],"we":[41,65],"examine":[42],"synthetic":[43,96],"generation":[45],"as":[46],"tool":[48],"extrapolate":[50],"difficult-to-obtain":[51],"high-resolution":[52],"by":[54],"combining":[55],"information":[56,131],"from":[57,79,90,116,132],"multiple":[58],"easier-to-obtain":[59],"lower-resolution":[60],"particular,":[64],"introduce":[66],"framework":[68],"uses":[70],"combination":[72,86],"of":[73,109,123,158],"univariate":[74],"multivariate":[76],"frequency":[77,88],"tables":[78,89],"given":[81],"target":[82,102,118],"geographical":[83],"location":[84,119],"in":[85,100,152],"with":[87,120],"other":[91],"auxiliary":[92,134],"locations":[93],"generate":[95],"microdata":[97],"individuals":[99],"the":[101,107,117,121,129,133,154,159,164,168],"location.":[103],"Our":[104],"method":[105],"combines":[106],"estimation":[108],"dependency":[111,156],"graph":[112],"conditional":[114],"probabilities":[115],"use":[122],"Gaussian":[125],"copula":[126],"leverage":[128],"available":[130],"locations.":[135],"We":[136],"perform":[137],"extensive":[138],"testing":[139],"on":[140,167],"two":[141],"datasets":[143],"demonstrate":[145],"our":[147],"approach":[148],"outperforms":[149],"prior":[150],"approaches":[151],"preserving":[153],"overall":[155],"structure":[157],"while":[161],"also":[162],"satisfying":[163],"constraints":[165],"defined":[166],"different":[169],"variables.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-15T23:13:30.683059","created_date":"2025-10-10T00:00:00"}