{"id":"https://openalex.org/W3139304791","doi":"https://doi.org/10.1109/tkde.2021.3068009","title":"Formal Analysis and Estimation of Chance in Datasets Based on Their Properties","display_name":"Formal Analysis and Estimation of Chance in Datasets Based on Their Properties","publication_year":2021,"publication_date":"2021-03-23","ids":{"openalex":"https://openalex.org/W3139304791","doi":"https://doi.org/10.1109/tkde.2021.3068009","mag":"3139304791"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3068009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3068009","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5035974041","display_name":"Abdel Aziz Taha","orcid":"https://orcid.org/0000-0002-7604-9041"},"institutions":[{"id":"https://openalex.org/I120221655","display_name":"Research Studios Austria","ror":"https://ror.org/04ry38w69","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I120221655"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Abdel Aziz Taha","raw_affiliation_strings":["RSA FG, Research Studio Data Science, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0002-7604-9041","affiliations":[{"raw_affiliation_string":"RSA FG, Research Studio Data Science, Vienna, Austria","institution_ids":["https://openalex.org/I120221655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088328122","display_name":"Luca Papariello","orcid":"https://orcid.org/0000-0003-1053-0163"},"institutions":[{"id":"https://openalex.org/I120221655","display_name":"Research Studios Austria","ror":"https://ror.org/04ry38w69","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I120221655"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Luca Papariello","raw_affiliation_strings":["RSA FG, Research Studio Data Science, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-1053-0163","affiliations":[{"raw_affiliation_string":"RSA FG, Research Studio Data Science, Vienna, Austria","institution_ids":["https://openalex.org/I120221655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087344250","display_name":"Alexandros Bampoulidis","orcid":"https://orcid.org/0000-0002-9423-4806"},"institutions":[{"id":"https://openalex.org/I120221655","display_name":"Research Studios Austria","ror":"https://ror.org/04ry38w69","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I120221655"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alexandros Bampoulidis","raw_affiliation_strings":["RSA FG, Research Studio Data Science, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0002-9423-4806","affiliations":[{"raw_affiliation_string":"RSA FG, Research Studio Data Science, Vienna, Austria","institution_ids":["https://openalex.org/I120221655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056018651","display_name":"Petr Knoth","orcid":"https://orcid.org/0000-0003-1161-7359"},"institutions":[{"id":"https://openalex.org/I120221655","display_name":"Research Studios Austria","ror":"https://ror.org/04ry38w69","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I120221655"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Petr Knoth","raw_affiliation_strings":["RSA FG, Research Studio Data Science, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RSA FG, Research Studio Data Science, Vienna, Austria","institution_ids":["https://openalex.org/I120221655"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003585648","display_name":"Mihai Lupu","orcid":"https://orcid.org/0000-0002-6328-6873"},"institutions":[{"id":"https://openalex.org/I120221655","display_name":"Research Studios Austria","ror":"https://ror.org/04ry38w69","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I120221655"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Mihai Lupu","raw_affiliation_strings":["RSA FG, Research Studio Data Science, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0002-6328-6873","affiliations":[{"raw_affiliation_string":"RSA FG, Research Studio Data Science, Vienna, Austria","institution_ids":["https://openalex.org/I120221655"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I120221655"],"apc_list":null,"apc_paid":null,"fwci":0.1365,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50906989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"34","issue":"12","first_page":"5784","last_page":"5795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9916999936103821,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9916999936103821,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9894999861717224,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8062677383422852},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.721112847328186},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.601783275604248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5807133913040161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5474942922592163},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4733576774597168},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47132208943367004},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4625093340873718},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.45343202352523804},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4328746795654297},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16755464673042297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11234503984451294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062677383422852},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.721112847328186},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.601783275604248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5807133913040161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5474942922592163},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4733576774597168},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47132208943367004},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4625093340873718},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45343202352523804},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4328746795654297},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16755464673042297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11234503984451294},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2021.3068009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3068009","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:oro.open.ac.uk:75770","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401187","display_name":"Open Research Online (The Open University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204136569","host_organization_name":"The Open University","host_organization_lineage":["https://openalex.org/I204136569"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1541459201","https://openalex.org/W1560107318","https://openalex.org/W1930624869","https://openalex.org/W1977868384","https://openalex.org/W1989393529","https://openalex.org/W2015887370","https://openalex.org/W2022165721","https://openalex.org/W2027902860","https://openalex.org/W2031167046","https://openalex.org/W2038894244","https://openalex.org/W2040032582","https://openalex.org/W2053154970","https://openalex.org/W2066873261","https://openalex.org/W2077922582","https://openalex.org/W2081649582","https://openalex.org/W2086702905","https://openalex.org/W2089468765","https://openalex.org/W2091947792","https://openalex.org/W2092095117","https://openalex.org/W2096045149","https://openalex.org/W2097554668","https://openalex.org/W2097569937","https://openalex.org/W2102831150","https://openalex.org/W2107956883","https://openalex.org/W2112560981","https://openalex.org/W2118522967","https://openalex.org/W2118978333","https://openalex.org/W2124125264","https://openalex.org/W2132886902","https://openalex.org/W2136487516","https://openalex.org/W2144981148","https://openalex.org/W2147717514","https://openalex.org/W2148405837","https://openalex.org/W2165533158","https://openalex.org/W2168532736","https://openalex.org/W2169658215","https://openalex.org/W2170314592","https://openalex.org/W2171083320","https://openalex.org/W2188829774","https://openalex.org/W2295598076","https://openalex.org/W2952752960","https://openalex.org/W2963265099","https://openalex.org/W2979966099","https://openalex.org/W3015571647","https://openalex.org/W3105571542","https://openalex.org/W3124333825","https://openalex.org/W4244528936","https://openalex.org/W6632397832","https://openalex.org/W6633497745","https://openalex.org/W6640462745"],"related_works":["https://openalex.org/W2965434730","https://openalex.org/W3106484983","https://openalex.org/W2766358358","https://openalex.org/W26882198","https://openalex.org/W4289860834","https://openalex.org/W244069490","https://openalex.org/W2463925622","https://openalex.org/W2107854016","https://openalex.org/W4283312760","https://openalex.org/W1992447679"],"abstract_inverted_index":{"Machine":[0],"learning":[1,46],"research,":[2],"particularly":[3],"in":[4,96],"genomics,":[5],"is":[6,99,117],"often":[7],"based":[8,62,139],"on":[9,44,63,75,82,106,140,177],"wide":[10,83],"shaped":[11,84],"datasets,":[12],"i.e.":[13],"datasets":[14,98,111],"having":[15],"a":[16,22,127],"large":[17],"number":[18,24,149,153],"of":[19,25,32,37,57,59,73,94,108,130,150,154,166,172],"features,":[20,151],"but":[21],"small":[23],"samples.":[26],"Such":[27],"configurations":[28],"raise":[29],"the":[30,45,49,55,71,92,118,141,148,152,157,167,173],"possibility":[31],"chance":[33,42,74,95,131,136,178],"influence":[34,72,93,132,137,179],"(the":[35],"increase":[36],"measured":[38],"accuracy":[39],"due":[40],"to":[41],"correlations)":[43],"process":[47],"and":[48,77,133,156,175],"evaluation":[50],"results.":[51],"Prior":[52],"research":[53],"underlined":[54],"problem":[56],"generalization":[58],"models":[60,104],"obtained":[61],"such":[64,97],"data.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,87,161],"investigate":[70],"prediction":[76,103],"show":[78],"its":[79,145],"significant":[80,91],"effects":[81],"datasets.":[85],"First,":[86],"empirically":[88],"demonstrate":[89],"how":[90],"by":[100],"showing":[101],"that":[102],"trained":[105],"thousands":[107],"randomly":[109],"generated":[110],"can":[112],"achieve":[113],"high":[114],"accuracy.":[115],"This":[116],"case":[119],"even":[120],"when":[121],"using":[122],"cross-validation.":[123],"We":[124],"then":[125],"provide":[126,162],"formal":[128,135,168],"analysis":[129,169],"design":[134],"estimators":[138],"dataset":[142],"parameters,":[143],"namely":[144],"sample":[146],"size,":[147],"classes":[155],"class":[158],"distribution.":[159],"Finally,":[160],"an":[163],"in-depth":[164],"discussion":[165],"including":[170],"applications":[171],"findings":[174],"recommendations":[176],"mitigation.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}