{"id":"https://openalex.org/W2087615914","doi":"https://doi.org/10.1145/1401890.1401915","title":"Anomaly pattern detection in categorical datasets","display_name":"Anomaly pattern detection in categorical datasets","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2087615914","doi":"https://doi.org/10.1145/1401890.1401915","mag":"2087615914"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401915","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and 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/A5101458264","display_name":"Kaustav Das","orcid":"https://orcid.org/0009-0002-5551-1441"},"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":true,"raw_author_name":"Kaustav Das","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055199976","display_name":"Jeff Schneider","orcid":"https://orcid.org/0000-0002-5080-9073"},"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":"Jeff Schneider","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067772128","display_name":"Daniel B. Neill","orcid":"https://orcid.org/0000-0001-6282-1240"},"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":"Daniel B. Neill","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101458264"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.8118,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.93615985,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9998000264167786,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9997000098228455,"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/T12391","display_name":"Artificial Immune Systems Applications","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7994608283042908},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.758963942527771},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.7044602036476135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6231448650360107},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5616341829299927},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5354727506637573},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5135095715522766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5055618286132812},{"id":"https://openalex.org/keywords/intrusion-detection-system","display_name":"Intrusion detection system","score":0.5029792189598083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3979877829551697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17256557941436768}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7994608283042908},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.758963942527771},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.7044602036476135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6231448650360107},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5616341829299927},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5354727506637573},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5135095715522766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5055618286132812},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.5029792189598083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3979877829551697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17256557941436768},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1401890.1401915","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.2394","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.2394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~neill/papers/kdd08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1543388142","https://openalex.org/W1763728792","https://openalex.org/W1974534365","https://openalex.org/W2005165739","https://openalex.org/W2039575199","https://openalex.org/W2105494575","https://openalex.org/W2105940436","https://openalex.org/W2110065044","https://openalex.org/W2123402141","https://openalex.org/W2127738598","https://openalex.org/W2129860818","https://openalex.org/W2150398577","https://openalex.org/W2153157120","https://openalex.org/W2161565143","https://openalex.org/W2162774438","https://openalex.org/W2595697910","https://openalex.org/W3144740773","https://openalex.org/W4300895248","https://openalex.org/W7023974811"],"related_works":["https://openalex.org/W2806741695","https://openalex.org/W4290647774","https://openalex.org/W3189286258","https://openalex.org/W3207797160","https://openalex.org/W3210364259","https://openalex.org/W4300558037","https://openalex.org/W2667207928","https://openalex.org/W2912112202","https://openalex.org/W4377864969","https://openalex.org/W3120251014"],"abstract_inverted_index":{"We":[0,13,107,141,180],"propose":[1,165],"a":[2,26,41,94,120],"new":[3],"method":[4,33],"for":[5],"detecting":[6],"patterns":[7,56,104,191],"of":[8,29,35,60,70,83,90,93,96,105,114,132,150,155,177],"anomalies":[9,16,71,151],"in":[10,99,123,152,192],"categorical":[11],"datasets.":[12],"assume":[14],"that":[15,182],"are":[17],"generated":[18],"by":[19,73,87,137],"some":[20],"underlying":[21],"process":[22],"which":[23,118],"affects":[24],"only":[25],"particular":[27],"subset":[28,95,113,154],"the":[30,58,68,74,84,97,115,129,133,138,148,156,178],"data.":[31,179,200],"Our":[32],"consists":[34],"two":[36],"steps:":[37],"we":[38,78],"first":[39],"use":[40],"\"local":[42],"anomaly":[43,76],"detector\"":[44],"to":[45,101,109,128,145,169,187],"identify":[46],"individual":[47],"records":[48,62],"with":[49],"anomalous":[50,61,124,190],"attribute":[51],"values,":[52],"and":[53,164,197],"then":[54],"detect":[55,102,110,189],"where":[57],"number":[59,149],"is":[63,159,185],"higher":[64,161],"than":[65,162],"expected.":[66],"Given":[67],"set":[69,89],"flagged":[72],"local":[75],"detector,":[77],"search":[79],"over":[80,173],"all":[81,174],"subsets":[82,176],"data":[85,117,158],"defined":[86],"any":[88,111,153],"fixed":[91],"values":[92],"attributes,":[98],"order":[100],"self-similar":[103],"anomalies.":[106],"wish":[108],"such":[112,175],"test":[116,157,172],"displays":[119],"significant":[121],"increase":[122],"activity":[125],"as":[126],"compared":[127],"normal":[130],"behavior":[131],"system":[134],"(as":[135],"indicated":[136],"training":[139],"data).":[140],"perform":[142,170],"significance":[143],"testing":[144],"determine":[146],"if":[147],"significantly":[160],"expected,":[163],"an":[166],"efficient":[167],"algorithm":[168,184],"this":[171,183],"show":[181],"able":[186],"accurately":[188],"real-world":[193],"hospital,":[194],"container":[195],"shipping":[196],"network":[198],"intrusion":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}