{"id":"https://openalex.org/W2280339326","doi":"https://doi.org/10.1145/3182383","title":"Generating Realistic Synthetic Population Datasets","display_name":"Generating Realistic Synthetic Population Datasets","publication_year":2018,"publication_date":"2018-04-16","ids":{"openalex":"https://openalex.org/W2280339326","doi":"https://doi.org/10.1145/3182383","mag":"2280339326"},"language":"en","primary_location":{"id":"doi:10.1145/3182383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3182383","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3182383","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3182383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101595027","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0002-4392-1307"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":"https://orcid.org/0000-0002-4392-1307","affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024383883","display_name":"Yue Ning","orcid":"https://orcid.org/0000-0002-1227-440X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Ning","raw_affiliation_strings":["Virginia Tech, Arlington, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103154375","display_name":"Prithwish Chakraborty","orcid":"https://orcid.org/0000-0003-1407-7677"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prithwish Chakraborty","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043872748","display_name":"Jilles Vreeken","orcid":"https://orcid.org/0000-0002-2310-2806"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jilles Vreeken","raw_affiliation_strings":["Max Planck Institute for Informatics and Saarland University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics and Saarland University, Germany","institution_ids":["https://openalex.org/I4210109712","https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067444605","display_name":"Nikolaj Tatti","orcid":"https://orcid.org/0000-0002-2087-5360"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Nikolaj Tatti","raw_affiliation_strings":["Aalto University, Aalto, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Aalto, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035052603","display_name":"Naren Ramakrishnan","orcid":"https://orcid.org/0000-0002-1821-9743"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naren Ramakrishnan","raw_affiliation_strings":["Virginia Tech, Arlington, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101595027"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.6273,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.82955484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":"4","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9843999743461609,"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"}},"topics":[{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9843999743461609,"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"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9779999852180481,"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/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"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/categorical-variable","display_name":"Categorical variable","score":0.7092905640602112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.675684928894043},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6265395283699036},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6092038154602051},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5207764506340027},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5193660855293274},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4811764657497406},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4634193480014801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4423118531703949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3167431354522705}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7092905640602112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.675684928894043},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6265395283699036},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6092038154602051},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5207764506340027},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5193660855293274},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4811764657497406},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4634193480014801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4423118531703949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3167431354522705},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/3182383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3182383","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3182383","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},{"id":"pmh:oai:escidoc.org:escidoc:2318749","is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002B-08F9-B","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/workingPaper"},{"id":"pmh:oai:escidoc.org:escidoc:2642859","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0002-16ED-B","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:figshare.com:article/24612615","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Generating_Realistic_Synthetic_Population_Datasets/24612615","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pure.mpg.de:item_2642859","is_oa":false,"landing_page_url":"https://hdl.handle.net/21.11116/0000-0002-16ED-B","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.60882/cispa.24612615.v1","is_oa":true,"landing_page_url":"https://doi.org/10.60882/cispa.24612615.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050916","display_name":"CISPA Helmholtz Center","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3182383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3182383","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3182383","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[{"id":"https://openalex.org/G1263469548","display_name":null,"funder_award_id":"1545362","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1825241773","display_name":null,"funder_award_id":"IIS-1633363","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2812462847","display_name":null,"funder_award_id":"D12PC000337","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5793192372","display_name":null,"funder_award_id":"W911NF-17-1-0021","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5907345857","display_name":null,"funder_award_id":"DGE-1545362 and IIS-1633363","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8778743723","display_name":null,"funder_award_id":"DGE-1545362","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8816249180","display_name":null,"funder_award_id":"1633363","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1493098199","https://openalex.org/W1537025923","https://openalex.org/W1539863007","https://openalex.org/W1548908134","https://openalex.org/W1564108952","https://openalex.org/W1974067702","https://openalex.org/W1992730709","https://openalex.org/W2001792610","https://openalex.org/W2021798868","https://openalex.org/W2029237138","https://openalex.org/W2049538695","https://openalex.org/W2051275939","https://openalex.org/W2055751864","https://openalex.org/W2064821617","https://openalex.org/W2076743544","https://openalex.org/W2083692482","https://openalex.org/W2105749831","https://openalex.org/W2107521066","https://openalex.org/W2111317215","https://openalex.org/W2117513046","https://openalex.org/W2121084172","https://openalex.org/W2124066753","https://openalex.org/W2140982038","https://openalex.org/W2146160048","https://openalex.org/W2150779766","https://openalex.org/W2151233483","https://openalex.org/W2151583733","https://openalex.org/W2154624311","https://openalex.org/W2157595172","https://openalex.org/W2158291508","https://openalex.org/W2160709761","https://openalex.org/W2295543610","https://openalex.org/W2342737791","https://openalex.org/W2404544143","https://openalex.org/W2497173630","https://openalex.org/W3100944407"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W2133382151","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"Modern":[0],"studies":[1],"of":[2,9,16,56,72,78,88,95],"societal":[3],"phenomena":[4],"rely":[5],"on":[6],"the":[7,93,96,120,134],"availability":[8],"large":[10,86],"datasets":[11,26,43,63,83],"capturing":[12],"attributes":[13],"and":[14,33,54,69,122,138,159,163],"activities":[15],"synthetic,":[17],"city-level,":[18],"populations.":[19],"For":[20],"instance,":[21],"in":[22,107],"epidemiology,":[23],"synthetic":[24,41,61],"population":[25,42,62],"are":[27,44,64,123],"necessary":[28,65],"to":[29,46,66,100,132],"study":[30],"disease":[31],"propagation":[32],"intervention":[34],"measures":[35],"before":[36],"implementation.":[37],"In":[38,58],"social":[39],"science,":[40],"needed":[45],"understand":[47],"how":[48,141],"policy":[49],"decisions":[50],"might":[51],"affect":[52],"preferences":[53],"behaviors":[55],"individuals.":[57,79],"public":[59],"health,":[60],"capture":[67],"diagnostic":[68],"procedural":[70],"characteristics":[71],"patient":[73],"records":[74],"without":[75],"violating":[76],"confidentialities":[77],"To":[80],"generate":[81],"such":[82,105],"over":[84],"a":[85,102,108],"set":[87],"categorical":[89],"variables,":[90],"we":[91,112,139],"propose":[92],"use":[94],"maximum":[97,135],"entropy":[98,136],"principle":[99],"formalize":[101],"generative":[103],"model":[104],"that":[106],"statistically":[109],"well-founded":[110],"way":[111],"can":[113],"optimally":[114],"utilize":[115],"given":[116],"prior":[117],"information":[118],"about":[119],"data,":[121],"unbiased":[124],"otherwise.":[125],"An":[126],"efficient":[127],"inference":[128],"algorithm":[129],"is":[130,144],"designed":[131],"estimate":[133],"model,":[137],"demonstrate":[140,164],"our":[142],"approach":[143,154],"adept":[145],"at":[146],"estimating":[147],"underlying":[148],"data":[149,158],"distributions.":[150],"We":[151],"evaluate":[152],"this":[153],"against":[155],"both":[156],"simulated":[157],"US":[160],"census":[161],"datasets,":[162],"its":[165],"feasibility":[166],"using":[167],"an":[168],"epidemic":[169],"simulation":[170],"application.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}