{"id":"https://openalex.org/W4415622298","doi":"https://doi.org/10.3389/fdata.2025.1604887","title":"Finding the needle in the haystack\u2014An interpretable sequential pattern mining method for classification problems","display_name":"Finding the needle in the haystack\u2014An interpretable sequential pattern mining method for classification problems","publication_year":2025,"publication_date":"2025-10-24","ids":{"openalex":"https://openalex.org/W4415622298","doi":"https://doi.org/10.3389/fdata.2025.1604887","pmid":"https://pubmed.ncbi.nlm.nih.gov/41230433"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2025.1604887","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1604887","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1604887/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1604887/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045150447","display_name":"Alexander Grote","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexander Grote","raw_affiliation_strings":["Institute for Information Systems (WIN), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Systems (WIN), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105367994","display_name":"Anuja Hariharan","orcid":"https://orcid.org/0009-0005-9743-6648"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anuja Hariharan","raw_affiliation_strings":["Institute for Information Systems (WIN), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Systems (WIN), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021007726","display_name":"Christof Weinhardt","orcid":"https://orcid.org/0000-0002-7945-4077"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christof Weinhardt","raw_affiliation_strings":["Institute for Information Systems (WIN), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Systems (WIN), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5045150447"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":{"value":1285,"currency":"USD","value_usd":1285},"apc_paid":{"value":1285,"currency":"USD","value_usd":1285},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41956056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"1604887","last_page":"1604887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.592199981212616,"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":0.592199981212616,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.1290999948978424,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.03750000149011612,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9265999794006348},{"id":"https://openalex.org/keywords/sequential-pattern-mining","display_name":"Sequential Pattern Mining","score":0.37139999866485596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3366999924182892},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.30720001459121704},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.27950000762939453}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9265999794006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384999752044678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5931000113487244},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49619999527931213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42559999227523804},{"id":"https://openalex.org/C149490388","wikidata":"https://www.wikidata.org/wiki/Q1718507","display_name":"Sequential Pattern Mining","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdata.2025.1604887","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1604887","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1604887/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:41230433","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41230433","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in big data","raw_type":null},{"id":"pmh:oai:doaj.org/article:1d2d1cd574054b70bcc472d683289c4c","is_oa":true,"landing_page_url":"https://doaj.org/article/1d2d1cd574054b70bcc472d683289c4c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, Vol 8 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11412870","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12604564","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fdata.2025.1604887","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2025.1604887","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1604887/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415622298.pdf","grobid_xml":"https://content.openalex.org/works/W4415622298.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W50012472","https://openalex.org/W97752496","https://openalex.org/W192347846","https://openalex.org/W600165676","https://openalex.org/W1491953564","https://openalex.org/W1549565124","https://openalex.org/W1596515083","https://openalex.org/W1608194207","https://openalex.org/W1700449338","https://openalex.org/W1909567488","https://openalex.org/W1972978214","https://openalex.org/W1973036367","https://openalex.org/W1979356656","https://openalex.org/W1990800901","https://openalex.org/W1992889781","https://openalex.org/W2004915807","https://openalex.org/W2009082127","https://openalex.org/W2014286755","https://openalex.org/W2019513593","https://openalex.org/W2024669491","https://openalex.org/W2024820855","https://openalex.org/W2029438113","https://openalex.org/W2029817244","https://openalex.org/W2033333157","https://openalex.org/W2040820996","https://openalex.org/W2046917428","https://openalex.org/W2052048969","https://openalex.org/W2072026441","https://openalex.org/W2079451707","https://openalex.org/W2092330360","https://openalex.org/W2092939357","https://openalex.org/W2100406636","https://openalex.org/W2102122585","https://openalex.org/W2102297485","https://openalex.org/W2104579579","https://openalex.org/W2110065044","https://openalex.org/W2111814036","https://openalex.org/W2115482638","https://openalex.org/W2116396873","https://openalex.org/W2120216197","https://openalex.org/W2147694185","https://openalex.org/W2154053567","https://openalex.org/W2166559705","https://openalex.org/W2185019360","https://openalex.org/W2295598076","https://openalex.org/W2338621248","https://openalex.org/W2510476599","https://openalex.org/W2791796577","https://openalex.org/W2892035503","https://openalex.org/W2910563713","https://openalex.org/W2945976633","https://openalex.org/W2963025680","https://openalex.org/W2964121744","https://openalex.org/W2965505261","https://openalex.org/W2968637290","https://openalex.org/W3002381343","https://openalex.org/W3004139501","https://openalex.org/W3014596384","https://openalex.org/W3017620100","https://openalex.org/W3092306916","https://openalex.org/W3118434586","https://openalex.org/W3126673261","https://openalex.org/W3157109194","https://openalex.org/W3171884590","https://openalex.org/W3187063016","https://openalex.org/W4224026768","https://openalex.org/W4235646468","https://openalex.org/W4238293282","https://openalex.org/W4243932450","https://openalex.org/W4252684946","https://openalex.org/W4285285341","https://openalex.org/W4288037554","https://openalex.org/W4291125983","https://openalex.org/W4299487748","https://openalex.org/W4360832008","https://openalex.org/W4383070246","https://openalex.org/W4384817234","https://openalex.org/W4386242314","https://openalex.org/W4388757207","https://openalex.org/W4389254196","https://openalex.org/W4390604658","https://openalex.org/W4400878172","https://openalex.org/W4401108892","https://openalex.org/W4401375098","https://openalex.org/W4402961411","https://openalex.org/W6888447827"],"related_works":[],"abstract_inverted_index":{"Introduction:":[0],"The":[1],"analysis":[2],"of":[3,21],"discrete":[4],"sequential":[5,23,49,65,155,187],"data,":[6],"such":[7],"as":[8],"event":[9],"logs":[10],"and":[11,34,112,122,139,149,174],"customer":[12],"clickstreams,":[13],"is":[14,94],"often":[15],"challenged":[16],"by":[17],"the":[18,68,72,100,181],"vast":[19],"number":[20],"possible":[22],"patterns.":[24],"This":[25,144],"complexity":[26],"makes":[27],"it":[28],"difficult":[29],"to":[30,77,82,131,177],"identify":[31],"meaningful":[32],"sequences":[33],"derive":[35],"actionable":[36],"insights.":[37],"Methods:":[38],"We":[39,98],"propose":[40],"a":[41,88,113,147],"novel":[42],"feature":[43,123,133],"selection":[44,134],"algorithm,":[45],"that":[46,93],"integrates":[47],"unsupervised":[48],"pattern":[50],"mining":[51,69],"with":[52,163,171],"supervised":[53],"machine":[54,59],"learning.":[55],"Unlike":[56],"existing":[57,83,178],"interpretable":[58,173],"learning":[60],"methods,":[61,179],"we":[62,86],"determine":[63],"important":[64,154],"patterns":[66,156],"during":[67],"process,":[70],"eliminating":[71],"need":[73],"for":[74,152,183],"post-hoc":[75],"classification":[76,128,158],"assess":[78],"their":[79],"relevance.":[80],"Compared":[81],"interesting":[84],"measures,":[85],"introduce":[87],"local,":[89],"class-specific":[90],"interestingness":[91],"measure":[92],"inherently":[95],"interpretable.":[96],"Results:":[97],"evaluated":[99],"algorithm":[101,168],"on":[102],"three":[103],"diverse":[104],"datasets":[105],"-":[106,116],"churn":[107],"prediction,":[108],"malware":[109],"sequence":[110],"analysis,":[111],"synthetic":[114],"dataset":[115],"covering":[117],"different":[118],"sizes,":[119],"application":[120],"domains,":[121],"complexities.":[124],"Our":[125],"method":[126],"achieved":[127],"performance":[129],"comparable":[130],"established":[132],"algorithms":[135],"while":[136],"maintaining":[137],"interpretability":[138,162],"reducing":[140],"computational":[141],"costs.":[142],"Discussion:":[143],"study":[145],"demonstrates":[146],"practical":[148],"efficient":[150,175],"approach":[151],"uncovering":[153],"in":[157,186],"tasks.":[159],"By":[160],"combining":[161],"competitive":[164],"predictive":[165],"performance,":[166],"our":[167],"provides":[169],"practitioners":[170],"an":[172],"alternative":[176],"paving":[180],"way":[182],"new":[184],"advances":[185],"data":[188],"analysis.":[189]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-28T00:00:00"}