{"id":"https://openalex.org/W2061100700","doi":"https://doi.org/10.1145/1081870.1081969","title":"Generation of synthetic data sets for evaluating the accuracy of knowledge discovery systems","display_name":"Generation of synthetic data sets for evaluating the accuracy of knowledge discovery systems","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2061100700","doi":"https://doi.org/10.1145/1081870.1081969","mag":"2061100700"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","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/A5034400738","display_name":"Daniel R. Jeske","orcid":"https://orcid.org/0000-0002-0214-7992"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel R. Jeske","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055617543","display_name":"Behrokh Samadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Behrokh Samadi","raw_affiliation_strings":["Lucent Technologies, Holmdel, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lucent Technologies, Holmdel, NJ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007872584","display_name":"Pengyue J. Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengyue J. Lin","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018320","display_name":"Lan Ye","orcid":"https://orcid.org/0009-0001-0290-5589"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan Ye","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055954499","display_name":"Sean Cox","orcid":"https://orcid.org/0000-0001-5546-7079"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Cox","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102930171","display_name":"Rui Xiao","orcid":"https://orcid.org/0009-0006-1655-4683"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Xiao","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111680529","display_name":"Ted Younglove","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ted Younglove","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042141088","display_name":"Minh Ly Duc","orcid":"https://orcid.org/0000-0003-0200-7153"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minh Ly","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108791214","display_name":"Douglas B. Holt","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Holt","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044967390","display_name":"Ryan Rich","orcid":"https://orcid.org/0000-0001-9495-3184"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Rich","raw_affiliation_strings":["University of California, Riverside, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5034400738"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":2.5428,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.91874125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"756","last_page":"762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987000226974487,"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/T11719","display_name":"Data Quality and Management","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8155470490455627},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6590756177902222},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5581132173538208},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48184287548065186},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4306245446205139},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.42895299196243286},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3453303575515747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23090654611587524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155470490455627},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6590756177902222},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5581132173538208},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48184287548065186},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4306245446205139},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.42895299196243286},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3453303575515747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23090654611587524},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1081870.1081969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.84.1081","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.1081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.collaboratory.ucr.edu/publications/Synthetic_Data_Sets.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W76845571","https://openalex.org/W1970583790","https://openalex.org/W2070452354","https://openalex.org/W2079641356","https://openalex.org/W2116456434","https://openalex.org/W2140421746","https://openalex.org/W2147826622","https://openalex.org/W2156795930","https://openalex.org/W2160150610","https://openalex.org/W3123678245"],"related_works":["https://openalex.org/W2758561209","https://openalex.org/W2250140425","https://openalex.org/W4281637929","https://openalex.org/W2734587838","https://openalex.org/W2091018730","https://openalex.org/W2592124422","https://openalex.org/W2734594493","https://openalex.org/W3194671208","https://openalex.org/W2390369089","https://openalex.org/W2389064843"],"abstract_inverted_index":{"Information":[0],"Discovery":[1],"and":[2,14,30,66,85,89,109,122,134,137],"Analysis":[3],"Systems":[4],"(IDAS)":[5],"are":[6,28],"designed":[7],"to":[8,19,81,153],"correlate":[9],"multiple":[10],"sources":[11],"of":[12,35,63,97,106,111,125],"data":[13,16,45,74,98,131],"use":[15],"mining":[17],"techniques":[18],"identify":[20],"potential":[21],"significant":[22],"events.":[23],"Application":[24],"domains":[25],"for":[26,40],"IDAS":[27,42,56,113],"numerous":[29],"include":[31],"the":[32,72,87,107,155],"emerging":[33],"area":[34],"homeland":[36],"security.Developing":[37],"test":[38,73,124],"cases":[39],"an":[41,78,104,112,126],"requires":[43],"background":[44],"sets":[46,75],"into":[47],"which":[48],"hypothetical":[49],"future":[50],"scenarios":[51],"can":[52,57,76],"be":[53,59,77],"overlaid.":[54],"The":[55,128],"then":[58],"measured":[60],"in":[61],"terms":[62],"false":[64,67],"positive":[65],"negative":[68],"error":[69],"rates.":[70],"Obtaining":[71],"obstacle":[79],"due":[80],"both":[82],"privacy":[83],"issues":[84],"also":[86,138],"time":[88],"cost":[90],"associated":[91],"with":[92],"collecting":[93],"a":[94,120],"diverse":[95],"set":[96],"sources.In":[99],"this":[100],"paper,":[101],"we":[102],"give":[103],"overview":[105],"design":[108],"architecture":[110],"Data":[114],"Set":[115],"Generator":[116],"(IDSG)":[117],"that":[118,141],"enables":[119],"fast":[121],"comprehensive":[123],"IDAS.":[127],"IDSG":[129],"generates":[130],"using":[132],"statistical":[133],"rule-based":[135],"algorithms":[136],"semantic":[139],"graphs":[140],"represent":[142],"interdependencies":[143],"between":[144],"attributes.":[145],"A":[146],"credit":[147],"card":[148],"transaction":[149],"application":[150],"is":[151],"used":[152],"illustrate":[154],"approach.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}