{"id":"https://openalex.org/W4220855543","doi":"https://doi.org/10.1007/s11634-022-00496-5","title":"Over-optimistic evaluation and reporting of novel cluster algorithms: an illustrative study","display_name":"Over-optimistic evaluation and reporting of novel cluster algorithms: an illustrative study","publication_year":2022,"publication_date":"2022-03-17","ids":{"openalex":"https://openalex.org/W4220855543","doi":"https://doi.org/10.1007/s11634-022-00496-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11634-022-00496-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11634-022-00496-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11634-022-00496-5.pdf","source":{"id":"https://openalex.org/S4210175730","display_name":"Advances in Data Analysis and Classification","issn_l":"1862-5347","issn":["1862-5347","1862-5355"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Data Analysis and Classification","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11634-022-00496-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040820559","display_name":"Theresa Ullmann","orcid":"https://orcid.org/0000-0003-1215-8561"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Theresa Ullmann","raw_affiliation_strings":["Institute for Medical Information Processing, Biometry, and Epidemiology, LMU Munich, Marchioninistr. 15, 81377, M\u00fcnchen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1215-8561","affiliations":[{"raw_affiliation_string":"Institute for Medical Information Processing, Biometry, and Epidemiology, LMU Munich, Marchioninistr. 15, 81377, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070112977","display_name":"Anna Beer","orcid":"https://orcid.org/0000-0002-6890-997X"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anna Beer","raw_affiliation_strings":["Institute for Informatics, LMU Munich, M\u00fcnchen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6890-997X","affiliations":[{"raw_affiliation_string":"Institute for Informatics, LMU Munich, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010805705","display_name":"Maximilian H\u00fcnem\u00f6rder","orcid":"https://orcid.org/0000-0001-9848-3714"},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Christian-Albrechts-Universit\u00e4t zu Kiel","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian H\u00fcnem\u00f6rder","raw_affiliation_strings":["Department of Computer Science, CAU Kiel, Kiel, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9848-3714","affiliations":[{"raw_affiliation_string":"Department of Computer Science, CAU Kiel, Kiel, Germany","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003335849","display_name":"Thomas Seidl","orcid":"https://orcid.org/0000-0002-4861-1412"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Seidl","raw_affiliation_strings":["Institute for Informatics, LMU Munich, M\u00fcnchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Informatics, LMU Munich, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015152016","display_name":"Anne\u2010Laure Boulesteix","orcid":"https://orcid.org/0000-0002-2729-0947"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anne-Laure Boulesteix","raw_affiliation_strings":["Institute for Medical Information Processing, Biometry, and Epidemiology, LMU Munich, Marchioninistr. 15, 81377, M\u00fcnchen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2729-0947","affiliations":[{"raw_affiliation_string":"Institute for Medical Information Processing, Biometry, and Epidemiology, LMU Munich, Marchioninistr. 15, 81377, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040820559"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.3873,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83812208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"211","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9998000264167786,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9941999912261963,"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":0.7683686017990112},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7555686831474304},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6953297853469849},{"id":"https://openalex.org/keywords/publication","display_name":"Publication","score":0.589055597782135},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5712640285491943},{"id":"https://openalex.org/keywords/optimism","display_name":"Optimism","score":0.5649999380111694},{"id":"https://openalex.org/keywords/competitor-analysis","display_name":"Competitor analysis","score":0.5323569774627686},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4680247902870178},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4274340569972992},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4075779318809509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33366116881370544},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14051294326782227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683686017990112},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7555686831474304},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6953297853469849},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.589055597782135},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5712640285491943},{"id":"https://openalex.org/C204017024","wikidata":"https://www.wikidata.org/wiki/Q485446","display_name":"Optimism","level":2,"score":0.5649999380111694},{"id":"https://openalex.org/C127576917","wikidata":"https://www.wikidata.org/wiki/Q624630","display_name":"Competitor analysis","level":2,"score":0.5323569774627686},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4680247902870178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4274340569972992},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4075779318809509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33366116881370544},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14051294326782227},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11634-022-00496-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11634-022-00496-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11634-022-00496-5.pdf","source":{"id":"https://openalex.org/S4210175730","display_name":"Advances in Data Analysis and Classification","issn_l":"1862-5347","issn":["1862-5347","1862-5355"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Data Analysis and Classification","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:spr:advdac:v:17:y:2023:i:1:d:10.1007_s11634-022-00496-5","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s11634-022-00496-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:106440","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-106440-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"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":"Advances in Data Analysis and Classification","raw_type":"doc-type:article"}],"best_oa_location":{"id":"doi:10.1007/s11634-022-00496-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11634-022-00496-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11634-022-00496-5.pdf","source":{"id":"https://openalex.org/S4210175730","display_name":"Advances in Data Analysis and Classification","issn_l":"1862-5347","issn":["1862-5347","1862-5355"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Data Analysis and Classification","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3467264548","display_name":null,"funder_award_id":"01IS18036A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220855543.pdf","grobid_xml":"https://content.openalex.org/works/W4220855543.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1979813476","https://openalex.org/W2005852722","https://openalex.org/W2040888993","https://openalex.org/W2051224630","https://openalex.org/W2055335745","https://openalex.org/W2075740080","https://openalex.org/W2092799168","https://openalex.org/W2104092906","https://openalex.org/W2115077250","https://openalex.org/W2127952499","https://openalex.org/W2135964318","https://openalex.org/W2142747423","https://openalex.org/W2150593711","https://openalex.org/W2154532634","https://openalex.org/W2164500538","https://openalex.org/W2165521059","https://openalex.org/W2192203593","https://openalex.org/W2211143780","https://openalex.org/W2505884832","https://openalex.org/W2524792501","https://openalex.org/W2562137041","https://openalex.org/W2740924709","https://openalex.org/W2770322578","https://openalex.org/W2809895662","https://openalex.org/W2949676527","https://openalex.org/W2987577970","https://openalex.org/W3090499726","https://openalex.org/W3125645198","https://openalex.org/W3126977189","https://openalex.org/W3134735565","https://openalex.org/W3162777509","https://openalex.org/W4231665431","https://openalex.org/W4235169531","https://openalex.org/W4299298909","https://openalex.org/W4300618951"],"related_works":["https://openalex.org/W2358804928","https://openalex.org/W4225710828","https://openalex.org/W1998528887","https://openalex.org/W2122713011","https://openalex.org/W2071729956","https://openalex.org/W2900331548","https://openalex.org/W2965538880","https://openalex.org/W2965399423","https://openalex.org/W2143282039","https://openalex.org/W2528370785"],"abstract_inverted_index":{"Abstract":[0],"When":[1],"researchers":[2,208],"publish":[3],"new":[4,35,215],"cluster":[5,68,104,142,153,181,216],"algorithms,":[6,36],"they":[7],"usually":[8],"demonstrate":[9,160],"the":[10,18,34,38,62,97,121,125,134,150,164,171,176,179,220,227,242],"strengths":[11],"of":[12,58,65,120,124,163,170,175,178,213,223,229],"their":[13,46,56,141],"novel":[14],"approaches":[15],"by":[16,82,136],"comparing":[17],"algorithms\u2019":[19],"performance":[20,64,144,186],"with":[21],"existing":[22],"competitors.":[23],"However,":[24],"such":[25],"studies":[26,80],"are":[27,115],"likely":[28],"to":[29,54,101,132,184,209],"be":[30,75,206],"optimistically":[31],"biased":[32],"towards":[33],"as":[37,48,50,156],"authors":[39],"have":[40,107],"a":[41,197,214],"vested":[42],"interest":[43],"in":[44,52,77,103,145,241],"presenting":[45],"method":[47],"favorably":[49],"possible":[51],"order":[53],"increase":[55],"chances":[57],"getting":[59],"published.":[60],"Therefore,":[61],"superior":[63],"newly":[66],"introduced":[67],"algorithms":[69,182],"is":[70,89,195],"over-optimistic":[71,147],"and":[72,84,112,174],"might":[73],"not":[74,118],"confirmed":[76],"independent":[78],"benchmark":[79,235],"performed":[81],"neutral":[83,234],"unbiased":[85],"authors.":[86],"This":[87,218],"problem":[88],"known":[90],"among":[91],"many":[92],"researchers,":[93],"but":[94],"so":[95],"far,":[96],"different":[98],"mechanisms":[99,135],"leading":[100],"over-optimism":[102,230],"algorithm":[105,154],"evaluation":[106],"never":[108],"been":[109],"systematically":[110],"studied":[111],"discussed.":[113],"Researchers":[114],"thus":[116,196],"often":[117],"aware":[119],"full":[122],"extent":[123],"problem.":[126],"We":[127],"present":[128],"an":[129,146,157],"illustrative":[130],"study":[131,194],"illuminate":[133],"which":[137,237],"authors\u2014consciously":[138],"or":[139,167],"unconsciously\u2014paint":[140],"algorithm\u2019s":[143,172],"light.":[148],"Using":[149],"recently":[151],"published":[152],"Rock":[155],"example,":[158],"we":[159,238],"how":[161,202],"optimization":[162],"used":[165],"datasets":[166],"data":[168],"characteristics,":[169],"parameters":[173],"choice":[177],"competing":[180],"leads":[183],"Rock\u2019s":[185],"appearing":[187],"better":[188],"than":[189],"it":[190,204],"actually":[191],"is.":[192],"Our":[193],"cautionary":[198],"tale":[199],"that":[200],"illustrates":[201],"easy":[203],"can":[205],"for":[207,225],"claim":[210],"apparent":[211],"\u201csuperiority\u201d":[212],"algorithm.":[217],"illuminates":[219],"vital":[221],"importance":[222],"strategies":[224],"avoiding":[226],"problems":[228],"(such":[231],"as,":[232],"e.g.,":[233],"studies),":[236],"also":[239],"discuss":[240],"article.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}