{"id":"https://openalex.org/W2736287575","doi":"https://doi.org/10.1145/2382577.2382579","title":"Leakage in data mining","display_name":"Leakage in data mining","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2736287575","doi":"https://doi.org/10.1145/2382577.2382579","mag":"2736287575"},"language":"en","primary_location":{"id":"doi:10.1145/2382577.2382579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2382577.2382579","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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 Transactions on Knowledge Discovery from Data","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/A5048628578","display_name":"Shachar Kaufman","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shachar Kaufman","raw_affiliation_strings":["Tel Aviv University, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039021124","display_name":"Saharon Rosset","orcid":"https://orcid.org/0000-0002-4458-9545"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Saharon Rosset","raw_affiliation_strings":["Tel Aviv University, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003651471","display_name":"Claudia Perlich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claudia Perlich","raw_affiliation_strings":["m6d"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"m6d","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009948451","display_name":"Ori Stitelman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ori Stitelman","raw_affiliation_strings":["m6d"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"m6d","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8356,"has_fulltext":false,"cited_by_count":598,"citation_normalized_percentile":{"value":0.88689183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"6","issue":"4","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9973000288009644,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9973000288009644,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9951000213623047,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9948999881744385,"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":0.6159883141517639},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.6156190037727356},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5967723727226257},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.555220901966095},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.36305081844329834},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.13193479180335999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6159883141517639},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.6156190037727356},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5967723727226257},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.555220901966095},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.36305081844329834},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.13193479180335999},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2382577.2382579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2382577.2382579","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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 Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G4643103907","display_name":null,"funder_award_id":"1227/09","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W46790137","https://openalex.org/W124884934","https://openalex.org/W1506509530","https://openalex.org/W1530010412","https://openalex.org/W1552694902","https://openalex.org/W1554944419","https://openalex.org/W1752500127","https://openalex.org/W1976645306","https://openalex.org/W2014289389","https://openalex.org/W2022775778","https://openalex.org/W2049910836","https://openalex.org/W2063014187","https://openalex.org/W2077061001","https://openalex.org/W2090243355","https://openalex.org/W2099085089","https://openalex.org/W2107968098","https://openalex.org/W2110603299","https://openalex.org/W2111322878","https://openalex.org/W2126371452","https://openalex.org/W2140937627","https://openalex.org/W2143891888","https://openalex.org/W2144620969","https://openalex.org/W2294309924","https://openalex.org/W2319794630","https://openalex.org/W2787894218","https://openalex.org/W3122118888","https://openalex.org/W4234286492","https://openalex.org/W4254300870","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"Deemed":[0],"\u201cone":[1],"of":[2,13,84,120,161,209,231],"the":[3,11,16,51,58,80,126,158,162,178,213,220],"top":[4],"ten":[5],"data":[6,17,44,92,163,195,221],"mining":[7,18,45,93,164],"mistakes\u201d,":[8],"leakage":[9,85,188,211,234],"is":[10,69,134,184,236],"introduction":[12],"information":[14],"about":[15],"target":[19],"that":[20,66,136,182,235],"should":[21],"not":[22,110],"be":[23,112],"legitimately":[24],"available":[25],"to":[26,31,111,115,171,186,194],"mine":[27],"from.":[28],"In":[29,141],"addition":[30],"our":[32,142],"own":[33],"industry":[34],"experience":[35],"with":[36,177,189],"real-life":[37,91],"projects,":[38,94],"controversies":[39],"around":[40],"several":[41,207],"major":[42],"public":[43],"competitions":[46,89],"held":[47],"recently":[48,139],"such":[49,122],"as":[50,70,73,123],"INFORMS":[52],"2010":[53],"Data":[54],"Mining":[55],"Challenge":[56,63],"and":[57,82,90,129,147,156,205],"IJCNN":[59],"2011":[60],"Social":[61],"Network":[62],"are":[64,149],"evidence":[65],"this":[67,100],"issue":[68],"relevant":[71],"today":[72],"it":[74,183],"has":[75,97,105,215],"ever":[76],"been.":[77],"While":[78],"acknowledging":[79],"importance":[81],"prevalence":[83],"in":[86],"both":[87],"synthetic":[88],"existing":[95],"literature":[96],"largely":[98],"left":[99],"idea":[101],"unexplored.":[102],"What":[103],"little":[104],"been":[106,138,223],"said":[107],"turns":[108],"out":[109],"broad":[113],"enough":[114],"cover":[116],"more":[117],"complex":[118],"cases":[119,146],"leakage,":[121],"those":[124],"where":[125],"classical":[127],"independently":[128],"identically":[130],"distributed":[131],"(i.i.d.)":[132],"assumption":[133],"violated,":[135],"have":[137,222],"documented.":[140],"new":[143],"approach,":[144],"these":[145],"others":[148],"explained":[150],"by":[151,198],"explicitly":[152],"defining":[153],"modeling":[154,241],"goals":[155],"analyzing":[157],"broader":[159],"framework":[160],"problem.":[165],"The":[166],"resulting":[167],"definition":[168],"enables":[169],"us":[170],"derive":[172],"general":[173],"methodology":[174],"for":[175],"dealing":[176],"issue.":[179],"We":[180,225],"show":[181],"possible":[185],"avoid":[187],"a":[190,202],"simple":[191],"specific":[192],"approach":[193],"management":[196],"followed":[197],"what":[199],"we":[200],"call":[201],"learn-predict":[203],"separation,":[204],"present":[206],"ways":[208],"detecting":[210],"when":[212],"modeler":[214],"no":[216],"control":[217],"over":[218],"how":[219],"collected.":[224],"also":[226],"offer":[227],"an":[228],"alternative":[229],"point":[230],"view":[232],"on":[233,238],"based":[237],"causal":[239],"graph":[240],"concepts.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":141},{"year":2025,"cited_by_count":91},{"year":2024,"cited_by_count":82},{"year":2023,"cited_by_count":77},{"year":2022,"cited_by_count":68},{"year":2021,"cited_by_count":54},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2025-10-10T00:00:00"}