{"id":"https://openalex.org/W2965505261","doi":"https://doi.org/10.1145/3292500.3332286","title":"Hypothesis Testing and Statistically-sound Pattern Mining","display_name":"Hypothesis Testing and Statistically-sound Pattern Mining","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2965505261","doi":"https://doi.org/10.1145/3292500.3332286","mag":"2965505261"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3332286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3332286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & 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/A5021603227","display_name":"Leonardo Pellegrina","orcid":"https://orcid.org/0000-0002-6601-5526"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Leonardo Pellegrina","raw_affiliation_strings":["Universit\u00e0 di Padova, Padua, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Padova, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021368473","display_name":"Matteo Riondato","orcid":"https://orcid.org/0000-0003-2523-4420"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matteo Riondato","raw_affiliation_strings":["Amherst College, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amherst College, Amherst, MA, USA","institution_ids":["https://openalex.org/I177605424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060279781","display_name":"Fabio Vandin","orcid":"https://orcid.org/0000-0003-2244-2320"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Vandin","raw_affiliation_strings":["Universit\u00e0 di Padova, Padua, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Padova, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021603227"],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":3.1713,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93094095,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3215","last_page":"3216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9855999946594238,"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":0.9836999773979187,"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":0.745337188243866},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6299524307250977},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.6044429540634155},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.47526973485946655},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45048850774765015},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4193170368671417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3251919150352478},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12820565700531006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10834798216819763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745337188243866},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6299524307250977},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.6044429540634155},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47526973485946655},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45048850774765015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4193170368671417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3251919150352478},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12820565700531006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10834798216819763},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3292500.3332286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3332286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:www.research.unipd.it:11577/3524907","is_oa":false,"landing_page_url":"https://hdl.handle.net/11577/3524907","pdf_url":null,"source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1496357020","https://openalex.org/W1596515083","https://openalex.org/W1963916765","https://openalex.org/W1978036582","https://openalex.org/W1979356656","https://openalex.org/W2014286755","https://openalex.org/W2030764200","https://openalex.org/W2036253883","https://openalex.org/W2062350863","https://openalex.org/W2095319945","https://openalex.org/W2104579579","https://openalex.org/W2110065044","https://openalex.org/W2110228583","https://openalex.org/W2167700118","https://openalex.org/W2290195878","https://openalex.org/W2301363727","https://openalex.org/W2338621248","https://openalex.org/W2418024629","https://openalex.org/W2568140450","https://openalex.org/W2742542169","https://openalex.org/W2754504587","https://openalex.org/W2796856748","https://openalex.org/W2801285565","https://openalex.org/W2809557135","https://openalex.org/W2905695809","https://openalex.org/W2950421339","https://openalex.org/W2963855376","https://openalex.org/W2964277278","https://openalex.org/W3103529187"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4205958290","https://openalex.org/W4386462264"],"abstract_inverted_index":{"The":[0],"availability":[1],"of":[2,9,25,109],"massive":[3],"datasets":[4],"has":[5],"highlighted":[6],"the":[7,23,26,62,82,90,107],"need":[8],"computationally":[10],"efficient":[11],"and":[12,46,71,92,124],"statistically-sound":[13],"methods":[14,41,111],"to":[15,32,49,79],"extracts":[16],"patterns":[17,54],"while":[18],"providing":[19],"rigorous":[20],"guarantees":[21],"on":[22],"quality":[24],"results,":[27],"in":[28,65,81,95,101,112],"particular":[29],"with":[30],"respect":[31],"false":[33],"discoveries.":[34],"In":[35],"this":[36],"tutorial":[37],"we":[38,105],"survey":[39],"recent":[40],"that":[42],"properly":[43],"combine":[44],"computational":[45,91],"statistical":[47,66,93],"considerations":[48],"efficiently":[50],"mine":[51],"statistically":[52],"reliable":[53],"from":[55],"large":[56],"datasets.":[57],"We":[58,86],"start":[59],"by":[60],"introducing":[61],"fundamental":[63],"concepts":[64],"hypothesis":[67],"testing,":[68],"including":[69],"conditional":[70],"unconditional":[72],"tests,":[73],"which":[74],"may":[75],"not":[76],"be":[77],"familiar":[78],"everyone":[80],"data":[83],"mining":[84,97],"community.":[85],"then":[87],"explain":[88],"how":[89],"challenges":[94],"pattern":[96],"have":[98],"been":[99],"tackled":[100],"different":[102],"ways.":[103],"Finally,":[104],"describe":[106],"application":[108],"these":[110],"areas":[113],"such":[114],"as":[115],"market":[116],"basket":[117],"analysis,":[118,123],"subgraph":[119],"mining,":[120],"social":[121],"networks":[122],"cancer":[125],"genomics.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}