{"id":"https://openalex.org/W2094947835","doi":"https://doi.org/10.1145/2601248.2601294","title":"Preliminary comparison of techniques for dealing with imbalance in software defect prediction","display_name":"Preliminary comparison of techniques for dealing with imbalance in software defect prediction","publication_year":2014,"publication_date":"2014-05-13","ids":{"openalex":"https://openalex.org/W2094947835","doi":"https://doi.org/10.1145/2601248.2601294","mag":"2094947835"},"language":"en","primary_location":{"id":"doi:10.1145/2601248.2601294","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2601248.2601294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://idus.us.es/handle/11441/42731","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033472437","display_name":"Daniel Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-2887-0185"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Daniel Rodriguez","raw_affiliation_strings":["University of Alcala, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"University of Alcala, Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047942214","display_name":"Israel Herraiz","orcid":"https://orcid.org/0000-0002-0582-7539"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Israel Herraiz","raw_affiliation_strings":["Technical Univ of Madrid (UPM), Madrid, Spain","Technical University of Madrid (UPM), Madrid, SPAIN"],"affiliations":[{"raw_affiliation_string":"Technical Univ of Madrid (UPM), Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Technical University of Madrid (UPM), Madrid, SPAIN","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039467248","display_name":"Rachel Harrison","orcid":"https://orcid.org/0000-0002-0636-7546"},"institutions":[{"id":"https://openalex.org/I124261462","display_name":"Oxford Brookes University","ror":"https://ror.org/04v2twj65","country_code":"GB","type":"education","lineage":["https://openalex.org/I124261462"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rachel Harrison","raw_affiliation_strings":["Oxford Brookes University, Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Oxford Brookes University, Oxford, UK","institution_ids":["https://openalex.org/I124261462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060412398","display_name":"Jos\u00e9 Javier Dolado","orcid":"https://orcid.org/0000-0002-3301-5650"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Dolado","raw_affiliation_strings":["Univ of the Basque Country, Donostia, Spain","Univ. of the Basque Country, Donostia, Spain"],"affiliations":[{"raw_affiliation_string":"Univ of the Basque Country, Donostia, Spain","institution_ids":[]},{"raw_affiliation_string":"Univ. of the Basque Country, Donostia, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036001529","display_name":"Jos\u00e9 C. Riquelme","orcid":"https://orcid.org/0000-0002-8243-2186"},"institutions":[{"id":"https://openalex.org/I79238269","display_name":"Universidad de Sevilla","ror":"https://ror.org/03yxnpp24","country_code":"ES","type":"education","lineage":["https://openalex.org/I79238269"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 C. Riquelme","raw_affiliation_strings":["University of Seville, Seville, Spain"],"affiliations":[{"raw_affiliation_string":"University of Seville, Seville, Spain","institution_ids":["https://openalex.org/I79238269"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033472437"],"corresponding_institution_ids":["https://openalex.org/I189268942"],"apc_list":null,"apc_paid":null,"fwci":19.633,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99121099,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9988999962806702,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9934999942779541,"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":0.8133753538131714},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7494354844093323},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6891223788261414},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5742310881614685},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.5103718638420105},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.48857054114341736},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46710219979286194},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.46529850363731384},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4518898129463196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4013935625553131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133753538131714},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7494354844093323},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6891223788261414},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5742310881614685},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.5103718638420105},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.48857054114341736},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46710219979286194},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46529850363731384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4518898129463196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4013935625553131},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2601248.2601294","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2601248.2601294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.588.8661","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.588.8661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.uah.es/drg/c/RHHDR_EASE14.pdf","raw_type":"text"},{"id":"pmh:oai:idus.us.es:11441/42731","is_oa":true,"landing_page_url":"https://idus.us.es/handle/11441/42731","pdf_url":null,"source":{"id":"https://openalex.org/S4306400333","display_name":"idUS (Universidad de Sevilla)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79238269","host_organization_name":"Universidad de Sevilla","host_organization_lineage":["https://openalex.org/I79238269"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:idus.us.es:11441/42731","is_oa":true,"landing_page_url":"https://idus.us.es/handle/11441/42731","pdf_url":null,"source":{"id":"https://openalex.org/S4306400333","display_name":"idUS (Universidad de Sevilla)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79238269","host_organization_name":"Universidad de Sevilla","host_organization_lineage":["https://openalex.org/I79238269"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W76990466","https://openalex.org/W168970045","https://openalex.org/W1485751654","https://openalex.org/W1504694836","https://openalex.org/W1505648523","https://openalex.org/W1536119330","https://openalex.org/W1563938718","https://openalex.org/W1565746575","https://openalex.org/W1570448133","https://openalex.org/W1941659294","https://openalex.org/W1964062576","https://openalex.org/W1964962870","https://openalex.org/W1975040830","https://openalex.org/W1976526581","https://openalex.org/W1988790447","https://openalex.org/W1992795012","https://openalex.org/W2006658471","https://openalex.org/W2017439596","https://openalex.org/W2048682095","https://openalex.org/W2058732827","https://openalex.org/W2073767361","https://openalex.org/W2076296473","https://openalex.org/W2088059023","https://openalex.org/W2096945460","https://openalex.org/W2097883090","https://openalex.org/W2099454382","https://openalex.org/W2104882279","https://openalex.org/W2105776892","https://openalex.org/W2107686700","https://openalex.org/W2109288821","https://openalex.org/W2109553965","https://openalex.org/W2112076978","https://openalex.org/W2119168155","https://openalex.org/W2119498311","https://openalex.org/W2125055259","https://openalex.org/W2130128436","https://openalex.org/W2130898128","https://openalex.org/W2136234086","https://openalex.org/W2137235241","https://openalex.org/W2146619110","https://openalex.org/W2148143831","https://openalex.org/W2149014999","https://openalex.org/W2150757437","https://openalex.org/W2151666086","https://openalex.org/W2158698691","https://openalex.org/W2160958420","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W2966207845","https://openalex.org/W2997546679","https://openalex.org/W6630328912"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Imbalanced":[0],"data":[1,7,27,52],"is":[2],"a":[3,17,126],"common":[4],"problem":[5,80],"in":[6,44,53,64,104],"mining":[8,28],"when":[9],"dealing":[10],"with":[11,46,84],"classification":[12],"problems,":[13],"where":[14],"samples":[15],"of":[16,81,111],"class":[18],"vastly":[19],"outnumber":[20],"other":[21],"classes.":[22],"In":[23],"this":[24,65],"situation,":[25],"many":[26],"algorithms":[29],"generate":[30],"poor":[31],"models":[32],"as":[33,125],"they":[34],"try":[35],"to":[36,78],"optimize":[37],"the":[38,79,92,105,109,112,115],"overall":[39],"accuracy":[40],"and":[41,55,63,75,114,121],"perform":[42],"badly":[43],"classes":[45],"very":[47],"few":[48],"samples.":[49],"Software":[50],"Engineering":[51],"general":[54],"defect":[56,82],"prediction":[57,83],"datasets":[58,86,95],"are":[59,102,123],"not":[60],"an":[61],"exception":[62],"paper,":[66],"we":[67],"compare":[68],"different":[69,85],"approaches,":[70],"namely":[71],"sampling,":[72],"cost-sensitive,":[73],"ensemble":[74],"hybrid":[76],"approaches":[77],"preprocessed":[87],"differently.":[88],"We":[89],"have":[90],"used":[91],"well-known":[93],"NASA":[94],"curated":[96],"by":[97],"Shepperd":[98],"et":[99],"al.":[100],"There":[101],"differences":[103],"results":[106],"depending":[107],"on":[108],"characteristics":[110],"dataset":[113],"evaluation":[116],"metrics,":[117],"especially":[118],"if":[119],"duplicates":[120],"inconsistencies":[122],"removed":[124],"preprocessing":[127],"step.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}