{"id":"https://openalex.org/W2046830558","doi":"https://doi.org/10.5167/uzh-25785","title":"Cross-project defect prediction: a large scale experiment on data vs. domain vs. process","display_name":"Cross-project defect prediction: a large scale experiment on data vs. domain vs. process","publication_year":2009,"publication_date":"2009-08-28","ids":{"openalex":"https://openalex.org/W2046830558","doi":"https://doi.org/10.5167/uzh-25785","mag":"2046830558"},"language":"en","primary_location":{"id":"pmh:oai:www.zora.uzh.ch:25785","doi":null,"is_oa":true,"landing_page_url":"https://www.zora.uzh.ch/id/eprint/25785/10/Zimmermann_Nagappan_Gall_Giger_Murphy_2009.pdf","pdf_url":"https://www.zora.uzh.ch/id/eprint/25785/10/Zimmermann_Nagappan_Gall_Giger_Murphy_2009.pdf","source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Zimmermann, Thomas; Nagappan, Nachiappan; Gall, Harald; Giger, Emanuel; Murphy, Brendan (2009). Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. In: 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering, Amsterdam, The Netherlands, 24 August 2009 - 28 August 2009. ACM, 91-100.","raw_type":"info:eu-repo/semantics/conferenceObject"},"parent_works":[],"lineage":["https://openalex.org/W2046830558"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.zora.uzh.ch/id/eprint/25785/10/Zimmermann_Nagappan_Gall_Giger_Murphy_2009.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061605447","display_name":"Thomas Zimmermann","orcid":"https://orcid.org/0000-0003-4905-1469","observed_orcids":["https://orcid.org/0000-0003-4905-1469"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zimmermann, Thomas","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101612061","display_name":"Nachiappan Nagappan","orcid":"https://orcid.org/0000-0003-1358-4124","observed_orcids":["https://orcid.org/0000-0003-1358-4124"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nagappan, Nachiappan","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009436227","display_name":"Harald C. Gall","orcid":"https://orcid.org/0000-0002-3874-5628","observed_orcids":["https://orcid.org/0000-0002-3874-5628"]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gall, Harald","raw_affiliation_strings":["University of Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-3874-5628","affiliations":[{"raw_affiliation_string":"University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003752547","display_name":"Emanuel Giger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Giger, Emanuel","raw_affiliation_strings":["University of Zurich, Zurich, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zurich, Zurich, USA#TAB#","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":null,"display_name":"Murphy, Brendan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Murphy, Brendan","raw_affiliation_strings":["Microsoft Research, Cambridge, United Kingdom ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, United Kingdom (","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.9158,"has_fulltext":false,"cited_by_count":716,"citation_normalized_percentile":{"value":0.99357509,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.00019999999494757503,"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"}},{"id":"https://openalex.org/T10430","display_name":"Software Engineering Techniques and Practices","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cross-project-defect-prediction","display_name":"cross-project defect prediction","score":0.9850000143051147},{"id":"https://openalex.org/keywords/software-defect-prediction","display_name":"software defect prediction","score":0.9760000109672546},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.6050000190734863},{"id":"https://openalex.org/keywords/domain-similarity","display_name":"domain similarity","score":0.5120000243186951},{"id":"https://openalex.org/keywords/software-development-process","display_name":"software development process","score":0.6620000004768372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096390724182129},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.6144615411758423},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5661365985870361},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5508617162704468},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.4717750549316406},{"id":"https://openalex.org/C15952604","wikidata":"https://www.wikidata.org/wiki/Q179012","display_name":"Project management","level":2,"score":0.464758038520813},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4301719069480896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4121546447277069},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3647775948047638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32062268257141113},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2507369816303253},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19240209460258484},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:www.zora.uzh.ch:25785","doi":null,"is_oa":true,"landing_page_url":"https://www.zora.uzh.ch/id/eprint/25785/10/Zimmermann_Nagappan_Gall_Giger_Murphy_2009.pdf","pdf_url":"https://www.zora.uzh.ch/id/eprint/25785/10/Zimmermann_Nagappan_Gall_Giger_Murphy_2009.pdf","source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Zimmermann, Thomas; Nagappan, Nachiappan; Gall, Harald; Giger, Emanuel; Murphy, Brendan (2009). Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. In: 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering, Amsterdam, The Netherlands, 24 August 2009 - 28 August 2009. ACM, 91-100.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:www.zora.uzh.ch:20.500.14742/46741","doi":null,"is_oa":true,"landing_page_url":"https://www.zora.uzh.ch/handle/20.500.14742/46741","pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zimmermann, T., Nagappan, N., Gall, H., Giger, E., & Murphy, B. (2009). Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. In V. Issarny & H. van Vliet (Eds.), ESEC/FSE \u201909: Proceedings of the the 7th joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on The foundations of software engineering (pp. 91\u2013100). ACM. https://doi.org/10.1145/1595696.1595713","raw_type":"Conference or Workshop Item"},{"id":"doi:10.5167/uzh-25785","doi":"https://doi.org/10.5167/uzh-25785","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-25785","pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:www.zora.uzh.ch:25785","doi":null,"is_oa":true,"landing_page_url":"https://www.zora.uzh.ch/id/eprint/25785/10/Zimmermann_Nagappan_Gall_Giger_Murphy_2009.pdf","pdf_url":"https://www.zora.uzh.ch/id/eprint/25785/10/Zimmermann_Nagappan_Gall_Giger_Murphy_2009.pdf","source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Zimmermann, Thomas; Nagappan, Nachiappan; Gall, Harald; Giger, Emanuel; Murphy, Brendan (2009). Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. In: 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering, Amsterdam, The Netherlands, 24 August 2009 - 28 August 2009. ACM, 91-100.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W66185676","https://openalex.org/W638916684","https://openalex.org/W1494282784","https://openalex.org/W1522987989","https://openalex.org/W1560022972","https://openalex.org/W1973540172","https://openalex.org/W1990259865","https://openalex.org/W1994410397","https://openalex.org/W2027483357","https://openalex.org/W2100945416","https://openalex.org/W2101227285","https://openalex.org/W2104364184","https://openalex.org/W2104789242","https://openalex.org/W2105300539","https://openalex.org/W2108161968","https://openalex.org/W2121866145","https://openalex.org/W2123127356","https://openalex.org/W2124797841","https://openalex.org/W2128666163","https://openalex.org/W2130287281","https://openalex.org/W2139855137","https://openalex.org/W2140190241","https://openalex.org/W2141051748","https://openalex.org/W2142481192","https://openalex.org/W2147105902","https://openalex.org/W2149783794","https://openalex.org/W2156482183","https://openalex.org/W2157922707","https://openalex.org/W2158864412","https://openalex.org/W2161074247","https://openalex.org/W2167926541","https://openalex.org/W2169171327","https://openalex.org/W3141989311","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W25935857","https://openalex.org/W2008596407","https://openalex.org/W2074218040","https://openalex.org/W2931627070","https://openalex.org/W2806036121","https://openalex.org/W2212842498","https://openalex.org/W2036055923","https://openalex.org/W4312433526","https://openalex.org/W2805185134","https://openalex.org/W2793567451"],"abstract_inverted_index":{"Prediction":[0],"of":[1,16,122],"software":[2,31,109],"defects":[3],"works":[4],"well":[5],"within":[6],"projects":[7,32,91],"as":[8,10],"long":[9],"there":[11],"is":[12,25,82,143],"a":[13,40,64,83,141],"sufficient":[14],"amount":[15],"data":[17],"available":[18],"to":[19,52,104],"train":[20],"any":[21],"models.":[22],"However,":[23],"this":[24,55],"rarely":[26],"the":[27,93,98,120],"case":[28],"for":[29,34,135],"new":[30],"and":[33,138],"many":[35],"companies.":[36],"So":[37],"far,":[38],"only":[39],"few":[41],"have":[42],"studies":[43],"focused":[44],"on":[45,63],"transferring":[46],"prediction":[47,61,81,142],"models":[48,62,89,112],"from":[49,90],"one":[50],"project":[51],"another.":[53],"In":[54],"paper,":[56],"we":[57,71,114],"study":[58],"cross-project":[59,74,80,123],"defect":[60],"large":[65],"scale.":[66],"For":[67],"12":[68],"real-world":[69],"applications,":[70],"ran":[72],"622":[73],"predictions.":[75,106,124],"Our":[76],"results":[77],"indicate":[78],"that":[79,117,130],"serious":[84],"challenge,":[85],"i.e.,":[86],"simply":[87],"using":[88],"in":[92],"same":[94,99],"domain":[95],"or":[96],"with":[97],"process":[100],"does":[101],"not":[102],"lead":[103],"accurate":[105],"To":[107],"help":[108],"engineers":[110],"choose":[111],"wisely,":[113],"identified":[115],"factors":[116],"do":[118],"influence":[119],"success":[121],"We":[125],"also":[126],"derived":[127],"decision":[128],"trees":[129],"can":[131],"provide":[132],"early":[133],"estimates":[134],"precision,":[136],"recall,":[137],"accuracy":[139],"before":[140],"attempted.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":39},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":50},{"year":2021,"cited_by_count":65},{"year":2020,"cited_by_count":64},{"year":2019,"cited_by_count":60},{"year":2018,"cited_by_count":73},{"year":2017,"cited_by_count":45},{"year":2016,"cited_by_count":55},{"year":2015,"cited_by_count":42},{"year":2014,"cited_by_count":40},{"year":2013,"cited_by_count":25},{"year":2012,"cited_by_count":24}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2016-06-24T00:00:00"}