{"id":"https://openalex.org/W2044879407","doi":"https://doi.org/10.1145/2020408.2020496","title":"Leakage in data mining","display_name":"Leakage in data mining","publication_year":2011,"publication_date":"2011-08-21","ids":{"openalex":"https://openalex.org/W2044879407","doi":"https://doi.org/10.1145/2020408.2020496","mag":"2044879407"},"language":"en","primary_location":{"id":"doi:10.1145/2020408.2020496","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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, Tel-Aviv, Israel","Tel Aviv University, Tel Aviv, Israel,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel-Aviv University, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, 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, Tel-Aviv, Israel","Tel Aviv University, Tel Aviv, Israel,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel-Aviv University, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel,","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","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":["Media6Degrees, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media6Degrees, New York, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8928,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":{"value":0.8657367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"556","last_page":"563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994999766349792,"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":0.9991999864578247,"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/leakage","display_name":"Leakage (economics)","score":0.657734215259552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6094605922698975},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5996811389923096},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5320780277252197},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.32517287135124207},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.12254399061203003}],"concepts":[{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.657734215259552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6094605922698975},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5996811389923096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5320780277252197},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.32517287135124207},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.12254399061203003},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2020408.2020496","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W46790137","https://openalex.org/W124884934","https://openalex.org/W1506509530","https://openalex.org/W1530010412","https://openalex.org/W1554944419","https://openalex.org/W1976645306","https://openalex.org/W2022775778","https://openalex.org/W2063014187","https://openalex.org/W2073404525","https://openalex.org/W2077061001","https://openalex.org/W2090243355","https://openalex.org/W2099085089","https://openalex.org/W2111322878","https://openalex.org/W2126371452","https://openalex.org/W2140937627","https://openalex.org/W2144620969","https://openalex.org/W2319794630","https://openalex.org/W2787894218","https://openalex.org/W2951118224","https://openalex.org/W3122118888","https://openalex.org/W4234286492","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],"\"one":[1],"of":[2,14,85,121,158,206],"the":[3,12,17,52,59,81,127,155,159,175,210,217],"top":[4],"ten":[5],"data":[6,18,45,93,160,192,218],"mining":[7,19,46,94,161],"mistakes\",":[8],"leakage":[9,86,185,208],"is":[10,70,131,181],"essentially":[11],"introduction":[13],"information":[15],"about":[16],"target,":[20],"which":[21],"should":[22],"not":[23,111],"be":[24,113],"legitimately":[25],"available":[26],"to":[27,32,112,116,168,183,191],"mine":[28],"from.":[29],"In":[30,138],"addition":[31],"our":[33,139],"own":[34],"industry":[35],"experience":[36],"with":[37,174,186],"real-life":[38,92],"projects,":[39,95],"controversies":[40],"around":[41],"several":[42,204],"major":[43],"public":[44],"competitions":[47,90],"held":[48],"recently":[49,136],"such":[50,123],"as":[51,71,74,124],"INFORMS":[53],"2010":[54],"Data":[55],"Mining":[56],"Challenge":[57,64],"and":[58,83,91,144,153,202],"IJCNN":[60],"2011":[61],"Social":[62],"Network":[63],"are":[65,146],"evidence":[66],"that":[67,133,179],"this":[68,101],"issue":[69],"relevant":[72],"today":[73],"it":[75,180],"has":[76,98,106,212],"ever":[77],"been.":[78],"While":[79],"acknowledging":[80],"importance":[82],"prevalence":[84],"in":[87],"both":[88],"synthetic":[89],"existing":[96],"literature":[97],"largely":[99],"left":[100],"idea":[102],"unexplored.":[103],"What":[104],"little":[105],"been":[107,135,220],"said":[108],"turns":[109],"out":[110],"broad":[114],"enough":[115],"cover":[117],"more":[118],"complex":[119],"cases":[120,143],"leakage,":[122],"those":[125],"where":[126],"classical":[128],"i.i.d.":[129],"assumption":[130],"violated,":[132],"have":[134,219],"documented.":[137],"new":[140],"approach,":[141],"these":[142],"others":[145],"explained":[147],"by":[148,195],"explicitly":[149],"defining":[150],"modeling":[151],"goals":[152],"analyzing":[154],"broader":[156],"framework":[157],"problem.":[162],"The":[163],"resulting":[164],"definition":[165],"enables":[166],"us":[167],"derive":[169],"general":[170],"methodology":[171],"for":[172],"dealing":[173],"issue.":[176],"We":[177],"show":[178],"possible":[182],"avoid":[184],"a":[187,199],"simple":[188],"specific":[189],"approach":[190],"management":[193],"followed":[194],"what":[196],"we":[197],"call":[198],"learn-predict":[200],"separation,":[201],"present":[203],"ways":[205],"detecting":[207],"when":[209],"modeler":[211],"no":[213],"control":[214],"over":[215],"how":[216],"collected.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}