{"id":"https://openalex.org/W2103281268","doi":"https://doi.org/10.1017/s0269888910000032","title":"A survey of data mining and knowledge discovery process models and methodologies","display_name":"A survey of data mining and knowledge discovery process models and methodologies","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2103281268","doi":"https://doi.org/10.1017/s0269888910000032","mag":"2103281268"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888910000032","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888910000032","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","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/A5102708088","display_name":"Gonzalo Mariscal","orcid":"https://orcid.org/0000-0001-7619-2190"},"institutions":[{"id":"https://openalex.org/I904013037","display_name":"Universidad Europea de Madrid","ror":"https://ror.org/04dp46240","country_code":"ES","type":"education","lineage":["https://openalex.org/I904013037"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Gonzalo Mariscal","raw_affiliation_strings":["Universidad Europea de Madrid, C/Tajo, S/N. 28670 - Villaciciosa de Odon, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Europea de Madrid, C/Tajo, S/N. 28670 - Villaciciosa de Odon, Madrid, Spain","institution_ids":["https://openalex.org/I904013037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027322725","display_name":"\u00d3scar Marb\u00e1n","orcid":"https://orcid.org/0000-0002-2465-1778"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00d3scar Marb\u00e1n","raw_affiliation_strings":["Facultad de Inform\u00e1tica, Universidad Polit\u00e9cnica de Madrid, Campus de Montegancedo, 28660 Boadilla del Monte, Madrid, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facultad de Inform\u00e1tica, Universidad Polit\u00e9cnica de Madrid, Campus de Montegancedo, 28660 Boadilla del Monte, Madrid, Spain#TAB#","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110800979","display_name":"C. Fernandez","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Covadonga Fern\u00e1ndez","raw_affiliation_strings":["Facultad de Inform\u00e1tica, Universidad Polit\u00e9cnica de Madrid, Campus de Montegancedo, 28660 Boadilla del Monte, Madrid, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facultad de Inform\u00e1tica, Universidad Polit\u00e9cnica de Madrid, Campus de Montegancedo, 28660 Boadilla del Monte, Madrid, Spain#TAB#","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102708088"],"corresponding_institution_ids":["https://openalex.org/I904013037"],"apc_list":null,"apc_paid":null,"fwci":9.2758,"has_fulltext":false,"cited_by_count":306,"citation_normalized_percentile":{"value":0.97731384,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"25","issue":"2","first_page":"137","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9810000061988831,"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/knowledge-extraction","display_name":"Knowledge extraction","score":0.8355278968811035},{"id":"https://openalex.org/keywords/software-mining","display_name":"Software mining","score":0.7457064390182495},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.696309506893158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.679862380027771},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6590747833251953},{"id":"https://openalex.org/keywords/business-process-discovery","display_name":"Business process discovery","score":0.6442657709121704},{"id":"https://openalex.org/keywords/process-mining","display_name":"Process mining","score":0.6196596622467041},{"id":"https://openalex.org/keywords/k-optimal-pattern-discovery","display_name":"K-optimal pattern discovery","score":0.5538430213928223},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5418326258659363},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.4713396728038788},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.46857213973999023},{"id":"https://openalex.org/keywords/work-in-process","display_name":"Work in process","score":0.2939983904361725},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14524918794631958},{"id":"https://openalex.org/keywords/business-process-management","display_name":"Business process management","score":0.1029764711856842},{"id":"https://openalex.org/keywords/business-process","display_name":"Business process","score":0.08838367462158203},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.08265310525894165},{"id":"https://openalex.org/keywords/business-process-modeling","display_name":"Business process modeling","score":0.07915481925010681}],"concepts":[{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.8355278968811035},{"id":"https://openalex.org/C103520596","wikidata":"https://www.wikidata.org/wiki/Q7554328","display_name":"Software mining","level":5,"score":0.7457064390182495},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.696309506893158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679862380027771},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6590747833251953},{"id":"https://openalex.org/C93453677","wikidata":"https://www.wikidata.org/wiki/Q1017580","display_name":"Business process discovery","level":5,"score":0.6442657709121704},{"id":"https://openalex.org/C124670913","wikidata":"https://www.wikidata.org/wiki/Q2608526","display_name":"Process mining","level":5,"score":0.6196596622467041},{"id":"https://openalex.org/C105445830","wikidata":"https://www.wikidata.org/wiki/Q6322855","display_name":"K-optimal pattern discovery","level":3,"score":0.5538430213928223},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5418326258659363},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4713396728038788},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.46857213973999023},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.2939983904361725},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14524918794631958},{"id":"https://openalex.org/C80309976","wikidata":"https://www.wikidata.org/wiki/Q7007379","display_name":"Business process management","level":4,"score":0.1029764711856842},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.08838367462158203},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08265310525894165},{"id":"https://openalex.org/C207505557","wikidata":"https://www.wikidata.org/wiki/Q4374012","display_name":"Business process modeling","level":4,"score":0.07915481925010681},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","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/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.0},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s0269888910000032","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888910000032","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},{"id":"pmh:oai:abacus.universidadeuropea.es:11268/827","is_oa":false,"landing_page_url":"http://hdl.handle.net/11268/827","pdf_url":null,"source":{"id":"https://openalex.org/S4306400164","display_name":"ABACUS. Repositorio de Producci\u00f3n Cient\u00edfica (Universidad Europea)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210101845","host_organization_name":"Universidad Europea","host_organization_lineage":["https://openalex.org/I4210101845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.550000011920929,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W49032594","https://openalex.org/W57948323","https://openalex.org/W62151500","https://openalex.org/W158652632","https://openalex.org/W409391466","https://openalex.org/W569988148","https://openalex.org/W1485658078","https://openalex.org/W1486051045","https://openalex.org/W1492070156","https://openalex.org/W1498727162","https://openalex.org/W1513495660","https://openalex.org/W1523293200","https://openalex.org/W1601529450","https://openalex.org/W1776383492","https://openalex.org/W1797782494","https://openalex.org/W1936022305","https://openalex.org/W2001254904","https://openalex.org/W2005538843","https://openalex.org/W2028470267","https://openalex.org/W2033626294","https://openalex.org/W2036296177","https://openalex.org/W2070808135","https://openalex.org/W2076732534","https://openalex.org/W2078946160","https://openalex.org/W2093456341","https://openalex.org/W2117769694","https://openalex.org/W2123140957","https://openalex.org/W2339588918","https://openalex.org/W2497389213","https://openalex.org/W2522166430","https://openalex.org/W2725766815","https://openalex.org/W2790987831","https://openalex.org/W2955223126","https://openalex.org/W2998778915","https://openalex.org/W3217434207","https://openalex.org/W4212848460","https://openalex.org/W4237578258"],"related_works":["https://openalex.org/W794897257","https://openalex.org/W2060045119","https://openalex.org/W4361214444","https://openalex.org/W2047547708","https://openalex.org/W4313357258","https://openalex.org/W4280494444","https://openalex.org/W2998184496","https://openalex.org/W2618942403","https://openalex.org/W3113298451","https://openalex.org/W4244739157"],"abstract_inverted_index":{"Abstract":[0],"Up":[1],"to":[2],"now,":[3],"many":[4],"data":[5,40,56,111,142,150,158,166],"mining":[6,41,57,112,143,151,159,167],"and":[7,11,32,35,42,46,58,62,97,121,144,160],"knowledge":[8,43,59,85,145,161],"discovery":[9,44,60,86,146,162],"methodologies":[10,45],"process":[12,47,147,152,168],"models":[13],"have":[14,77],"been":[15],"developed,":[16],"with":[17],"varying":[18],"degrees":[19],"of":[20,52,67,82,99,108,135,157],"success.":[21],"In":[22],"this":[23,71],"paper,":[24],"we":[25,76,138],"describe":[26],"the":[27,65,68,83,118,128,136],"most":[28],"used":[29],"(in":[30,37],"industrial":[31],"academic":[33],"projects)":[34],"cited":[36],"scientific":[38],"literature)":[39],"models,":[48],"providing":[49],"an":[50],"overview":[51],"its":[53],"evolution":[54],"along":[55],"history":[61],"setting":[63],"down":[64],"state":[66],"art":[69],"in":[70,87,123],"topic.":[72],"For":[73],"every":[74,100,125],"approach,":[75],"provided":[78],"a":[79,105,133,140],"brief":[80],"description":[81],"proposed":[84],"databases":[88],"(KDD)":[89],"process,":[90],"discussing":[91],"about":[92],"special":[93],"features,":[94],"outstanding":[95],"advantages":[96],"disadvantages":[98],"approach.":[101],"Apart":[102],"from":[103,175],"that,":[104],"global":[106],"comparative":[107],"all":[109],"presented":[110],"approaches":[113],"is":[114,169],"provided,":[115],"focusing":[116],"on":[117,171],"different":[119],"steps":[120,173],"tasks":[122],"which":[124],"approach":[126],"interprets":[127],"whole":[129],"KDD":[130],"process.":[131],"As":[132],"result":[134],"comparison,":[137],"propose":[139],"new":[141],"named":[148],"refined":[149,165],"for":[153],"developing":[154],"any":[155],"kind":[156],"project.":[163],"The":[164],"built":[170],"specific":[172],"taken":[174],"analyzed":[176],"approaches.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":27},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}
