{"id":"https://openalex.org/W4383199656","doi":"https://doi.org/10.1145/3606274.3606277","title":"The Need for Unsupervised Outlier Model Selection: A Review and Evaluation of Internal Evaluation Strategies","display_name":"The Need for Unsupervised Outlier Model Selection: A Review and Evaluation of Internal Evaluation Strategies","publication_year":2023,"publication_date":"2023-06-22","ids":{"openalex":"https://openalex.org/W4383199656","doi":"https://doi.org/10.1145/3606274.3606277"},"language":"en","primary_location":{"id":"doi:10.1145/3606274.3606277","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606274.3606277","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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 SIGKDD Explorations Newsletter","raw_type":"journal-article"},"type":"review","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/A5110759343","display_name":"Quint\u00edn Mart\u00edn Mart\u00edn","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Q. Ma","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057711796","display_name":"Yue Zhao","orcid":"https://orcid.org/0000-0003-3401-4921"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114833329","display_name":"Xiaorong Zhang","orcid":"https://orcid.org/0000-0002-9008-1857"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaorong Zhang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001634795","display_name":"Leman Akoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leman Akoglu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8948,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96121096,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"25","issue":"1","first_page":"19","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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/T11220","display_name":"Water Systems and Optimization","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9858999848365784,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8532911539077759},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7949221730232239},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6585710644721985},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6504908800125122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6402798891067505},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6090192198753357},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5614736080169678},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5284934639930725},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.5134202241897583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5049946904182434},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49760177731513977},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4332151412963867},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4203597903251648},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40766799449920654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8532911539077759},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7949221730232239},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6585710644721985},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6504908800125122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6402798891067505},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6090192198753357},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5614736080169678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5284934639930725},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.5134202241897583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5049946904182434},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49760177731513977},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4332151412963867},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4203597903251648},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40766799449920654},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3606274.3606277","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606274.3606277","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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 SIGKDD Explorations Newsletter","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W199035648","https://openalex.org/W309312769","https://openalex.org/W1242748811","https://openalex.org/W1981202432","https://openalex.org/W1986332411","https://openalex.org/W1992276041","https://openalex.org/W1996747841","https://openalex.org/W2061240327","https://openalex.org/W2097714558","https://openalex.org/W2112213600","https://openalex.org/W2129281431","https://openalex.org/W2132870739","https://openalex.org/W2138621811","https://openalex.org/W2160450239","https://openalex.org/W2282861635","https://openalex.org/W2336788611","https://openalex.org/W2337344967","https://openalex.org/W2472119793","https://openalex.org/W2584401436","https://openalex.org/W2622889010","https://openalex.org/W2626241468","https://openalex.org/W2746499228","https://openalex.org/W2774228929","https://openalex.org/W2910966739","https://openalex.org/W2914827665","https://openalex.org/W2953301799","https://openalex.org/W2976723666","https://openalex.org/W2990138404","https://openalex.org/W3011522541","https://openalex.org/W3037212379","https://openalex.org/W3039137796","https://openalex.org/W3089028909","https://openalex.org/W3156880769","https://openalex.org/W3212272194","https://openalex.org/W4212937970","https://openalex.org/W4238297360","https://openalex.org/W4241492760","https://openalex.org/W4283028913","https://openalex.org/W4306815936","https://openalex.org/W6606677274","https://openalex.org/W6608319088","https://openalex.org/W6649652859","https://openalex.org/W6687328954","https://openalex.org/W6690804842","https://openalex.org/W6697265569","https://openalex.org/W6739124637","https://openalex.org/W6762858396","https://openalex.org/W6772671741","https://openalex.org/W6803693056","https://openalex.org/W6839719062","https://openalex.org/W6846220733"],"related_works":["https://openalex.org/W4295309597","https://openalex.org/W4322775603","https://openalex.org/W4210794429","https://openalex.org/W4362544620","https://openalex.org/W1595351371","https://openalex.org/W3116762327","https://openalex.org/W2230433129","https://openalex.org/W2606848831","https://openalex.org/W4375930479","https://openalex.org/W4384389885"],"abstract_inverted_index":{"Given":[0],"an":[1],"unsupervised":[2,60,154,303],"outlier":[3,25,84,142,304],"detection":[4,12,39,199,232],"task,":[5],"how":[6],"should":[7],"one":[8],"select":[9],"i)":[10],"a":[11,21,89,102,194,241,310],"algorithm,":[13],"and":[14,41,116,175,201,210,249,266,296,307],"ii)":[15],"associated":[16],"hyperparameter":[17],"values":[18,51],"(jointly":[19],"called":[20],"model)?":[22],"E":[23],"ective":[24,302],"model":[26,61,96,132,305],"selection":[27,62,174],"is":[28,63,79],"essential":[29],"as":[30,144,146,172,309],"di":[31,221,262],"erent":[32,222,263],"algorithms":[33],"may":[34],"work":[35,92,314],"well":[36,145],"for":[37,100,141,288,300,312],"varying":[38],"tasks,":[40],"moreover":[42],"their":[43,162,225],"performance":[44],"can":[45,149],"be":[46,150,253,286],"quite":[47],"sensitive":[48],"to":[49,168,227,285],"the":[50,53,57,67,77,83,111,117,122,153,176,247,293,297,316],"of":[52,69,91,121,206,246,295],"hyperparameters":[54],"(HPs).":[55],"On":[56],"other":[58],"hand,":[59],"notoriously":[64],"difficult,":[65],"in":[66,82,166],"absence":[68],"hold-out":[70],"validation":[71],"data":[72,113],"with":[73,183,197],"ground-truth":[74],"labels.":[75,237],"Therefore,":[76],"problem":[78],"vastly":[80],"understudied":[81],"mining":[85],"literature.":[86,158],"There":[87],"exists":[88],"body":[90],"that":[93,148,244],"propose":[94],"internal":[95,106,131,217],"evaluation":[97,133],"strate-":[98],"gies":[99],"selecting":[101],"model.":[103],"These":[104],"so-called":[105],"strategies":[107,134,218,251],"solely":[108],"rely":[109],"on":[110,224,315],"input":[112],"(without":[114],"labels)":[115],"output":[118],"(outlier":[119],"scores)":[120],"candidate":[123,203,282],"models.":[124],"In":[125],"this":[126,187],"paper,":[127],"we":[128,160,189],"rst":[129],"survey":[130,291],"including":[135],"both":[136],"those":[137,147],"proposed":[138],"speci":[139],"cally":[140],"detection,":[143],"adapted":[151,250],"from":[152,219,264],"deep":[155],"representation":[156],"learning":[157],"Then,":[159],"investigate":[161],"e":[163,301],"ectiveness":[164],"empirically":[165],"comparison":[167],"simple":[169],"baselines":[170],"such":[171],"random":[173],"popular":[177],"state-of-the-art":[178],"detector":[179],"Isolation":[180],"Forest":[181],"(iForest)":[182],"default":[184,274],"HPs.":[185],"To":[186],"end,":[188],"set":[190],"up":[191],"(and":[192],"open-source)":[193],"large":[195],"testbed":[196],"39":[198],"tasks":[200],"297":[202],"models":[204,230,283],"comprised":[205],"8":[207],"different":[208],"detectors":[209],"various":[211],"HP":[212],"con":[213],"gurations.":[214],"We":[215],"evaluate":[216],"7":[220],"families":[223],"ability":[226],"discriminate":[228],"between":[229],"w.r.t.":[231],"performance,":[233],"without":[234],"using":[235],"any":[236],"Our":[238,290],"study":[239],"reports":[240],"striking":[242],"nding,":[243],"none":[245],"existing":[248],"would":[252],"practically":[254],"useful:":[255],"stand-alone":[256],"ones":[257,268],"are":[258],"not":[259,270],"signi":[260],"cantly":[261],"random,":[265],"consensus-based":[267],"do":[269],"outperform":[271],"iForest":[272],"(w/":[273],"HPs)":[275],"while":[276],"being":[277],"more":[278],"expensive":[279],"(as":[280],"all":[281],"need":[284,299],"trained":[287],"evaluation).":[289],"stresses":[292],"importance":[294],"standing":[298],"selection,":[306],"acts":[308],"call":[311],"future":[313],"problem.":[317]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}