{"id":"https://openalex.org/W4410049462","doi":"https://doi.org/10.1145/3676151.3719368","title":"Quantifying Data Leakage in Failure Prediction Tasks","display_name":"Quantifying Data Leakage in Failure Prediction Tasks","publication_year":2025,"publication_date":"2025-05-03","ids":{"openalex":"https://openalex.org/W4410049462","doi":"https://doi.org/10.1145/3676151.3719368"},"language":"en","primary_location":{"id":"doi:10.1145/3676151.3719368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676151.3719368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/SPEC International Conference on Performance Engineering","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/A5096717916","display_name":"Daniel Grillmeyer","orcid":"https://orcid.org/0009-0009-0997-4227"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Grillmeyer","raw_affiliation_strings":["University of W\u00fcrzburg, W\u00fcrzburg, Germany"],"raw_orcid":"https://orcid.org/0009-0009-0997-4227","affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg, W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057396498","display_name":"Marius Hadry","orcid":"https://orcid.org/0000-0002-3602-5790"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marius Hadry","raw_affiliation_strings":["University of W\u00fcrzburg, W\u00fcrzburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3602-5790","affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg, W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088400510","display_name":"Veronika Lesch","orcid":"https://orcid.org/0000-0001-7481-4099"},"institutions":[{"id":"https://openalex.org/I108806672","display_name":"Baden-Wuerttemberg Cooperative State University","ror":"https://ror.org/02xdzy536","country_code":"DE","type":"education","lineage":["https://openalex.org/I108806672"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Veronika Lesch","raw_affiliation_strings":["Baden-Wuerttemberg Cooperative State University Mosbach, Mosbach, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7481-4099","affiliations":[{"raw_affiliation_string":"Baden-Wuerttemberg Cooperative State University Mosbach, Mosbach, Germany","institution_ids":["https://openalex.org/I108806672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009503573","display_name":"Vanessa Borst","orcid":"https://orcid.org/0009-0004-7123-7934"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vanessa Borst","raw_affiliation_strings":["University of W\u00fcrzburg, W\u00fcrzburg, Germany"],"raw_orcid":"https://orcid.org/0009-0004-7123-7934","affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg, W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018956019","display_name":"Robert Leppich","orcid":"https://orcid.org/0000-0003-4711-7743"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Leppich","raw_affiliation_strings":["University of W\u00fcrzburg, W\u00fcrzburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4711-7743","affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg, W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063155276","display_name":"Andr\u00e9 Bauer","orcid":"https://orcid.org/0000-0002-5582-8812"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Bauer","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0002-5582-8812","affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013790674","display_name":"Samuel Kounev","orcid":"https://orcid.org/0000-0001-9742-2063"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Samuel Kounev","raw_affiliation_strings":["University of W\u00fcrzburg, W\u00fcrzburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9742-2063","affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg, W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80466527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"334","last_page":"346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9957000017166138,"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"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.666410505771637},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.6187682747840881},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.5377339124679565},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3335566520690918},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14041125774383545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666410505771637},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.6187682747840881},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5377339124679565},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3335566520690918},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14041125774383545},{"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:10.1145/3676151.3719368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676151.3719368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4300000071525574,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2319441181","https://openalex.org/W2736287575","https://openalex.org/W2784247142","https://openalex.org/W2900006920","https://openalex.org/W2946048830","https://openalex.org/W2994457981","https://openalex.org/W2997591727","https://openalex.org/W3035026109","https://openalex.org/W3090155366","https://openalex.org/W3107370826","https://openalex.org/W3138290087","https://openalex.org/W3184231327","https://openalex.org/W4206669279","https://openalex.org/W4385576721","https://openalex.org/W6912515347"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"With":[0],"the":[1,54,101,118,141,177,180,195],"ever":[2],"increasing":[3],"importance":[4],"of":[5,19,33,103,120,140,144,168,179,198],"cloud":[6],"computing":[7],"and":[8,42,71,84,125,134,194],"a":[9,16,79,111],"strong":[10],"focus":[11],"on":[12,24,100],"reliable":[13],"data":[14,90,102,113,121,163,182],"centers,":[15],"high":[17],"amount":[18,119],"research":[20],"has":[21,74],"been":[22,66],"done":[23],"failure":[25,63],"prediction":[26,64,199],"for":[27,61,116],"hard":[28],"disk":[29],"drives.":[30],"The":[31],"collection":[32],"monitoring":[34],"data,":[35],"such":[36],"as":[37,185,187],"SMART":[38],"statistics":[39],"(Self-Monitoring,":[40],"Analysis,":[41],"Reporting":[43],"Technology)":[44],"from":[45],"operational":[46],"HDDs,":[47],"enables":[48],"operators":[49],"to":[50,89,149,162,175],"obtain":[51],"predictions":[52],"about":[53],"expected":[55],"remaining":[56],"useful":[57],"life.":[58],"Numerous":[59],"methods":[60],"HDD":[62],"have":[65],"published":[67],"in":[68,123,138],"recent":[69],"years,":[70],"their":[72],"evaluation":[73],"shown":[75],"decent":[76],"results.":[77],"However,":[78],"naive":[80],"splitting":[81,132,152,159,192],"into":[82],"training":[83,124],"test":[85,126],"sets":[86],"can":[87],"lead":[88],"leakage":[91,114,122,164,183],"and,":[92],"thus,":[93],"over-optimistic":[94],"results":[95,155],"that":[96,158],"cannot":[97],"be":[98],"achieved":[99],"scientific":[104],"interest.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109,129,172],"propose":[110],"novel":[112],"measure":[115,137],"quantifying":[117],"datasets.":[127],"Further,":[128],"define":[130],"four":[131],"techniques":[133,160,193],"evaluate":[135],"our":[136],"terms":[139],"performance":[142,196],"optimism":[143,197],"classification":[145],"models":[146],"with":[147,190],"respect":[148],"these":[150],"different":[151,191],"strategies.":[153],"Our":[154],"consistently":[156],"show":[157,176],"prone":[161],"induce":[165],"an":[166],"overestimation":[167],"predictive":[169],"performance.":[170],"Overall,":[171],"were":[173],"able":[174],"usefulness":[178],"defined":[181],"measure,":[184],"well":[186],"its":[188],"connection":[189],"models.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
