{"id":"https://openalex.org/W4416564928","doi":"https://doi.org/10.1007/s11334-025-00623-3","title":"Impact of class balancing techniques or events per variable ratio on the conclusion of the software faults prediction models","display_name":"Impact of class balancing techniques or events per variable ratio on the conclusion of the software faults prediction models","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416564928","doi":"https://doi.org/10.1007/s11334-025-00623-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11334-025-00623-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11334-025-00623-3","pdf_url":null,"source":{"id":"https://openalex.org/S151239915","display_name":"Innovations in Systems and Software Engineering","issn_l":"1614-5046","issn":["1614-5046","1614-5054"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Innovations in Systems and Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11334-025-00623-3","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101987074","display_name":"Asad Ali","orcid":"https://orcid.org/0000-0001-7465-1090"},"institutions":[{"id":"https://openalex.org/I202376891","display_name":"Sarhad University of Science and Information Technology","ror":"https://ror.org/04dx2y384","country_code":"PK","type":"education","lineage":["https://openalex.org/I202376891"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Asad Ali","raw_affiliation_strings":["Department of Computer Science/IT, Sarhad University, Peshawar, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science/IT, Sarhad University, Peshawar, Pakistan","institution_ids":["https://openalex.org/I202376891"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102775089","display_name":"Dost Muhammad","orcid":"https://orcid.org/0000-0001-9186-6392"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Dost Muhammad","raw_affiliation_strings":["CRT-AI and ADAPT Research Centres, School of Computer Science, University of Galway, Galway, Ireland"],"affiliations":[{"raw_affiliation_string":"CRT-AI and ADAPT Research Centres, School of Computer Science, University of Galway, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008335398","display_name":"Mushtaq Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I195024194","display_name":"Riphah International University","ror":"https://ror.org/02kdm5630","country_code":"PK","type":"education","lineage":["https://openalex.org/I195024194"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Mushtaq Ali","raw_affiliation_strings":["Faculty of Computing, Riphah International University, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Riphah International University, Islamabad, Pakistan","institution_ids":["https://openalex.org/I195024194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009740771","display_name":"Fakhrud Din","orcid":"https://orcid.org/0000-0001-5025-3223"},"institutions":[{"id":"https://openalex.org/I68649149","display_name":"University of Malakand","ror":"https://ror.org/012xdha97","country_code":"PK","type":"education","lineage":["https://openalex.org/I68649149"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Fakhrud Din","raw_affiliation_strings":["Department of Computer Science & IT, University of Malakand, Lower Dir, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & IT, University of Malakand, Lower Dir, Pakistan","institution_ids":["https://openalex.org/I68649149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102775089"],"corresponding_institution_ids":["https://openalex.org/I188760350"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50623374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"1","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":0.9079999923706055,"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":0.9079999923706055,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.04749999940395355,"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/T12127","display_name":"Software System Performance and Reliability","score":0.010900000110268593,"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/classifier","display_name":"Classifier (UML)","score":0.6449999809265137},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5400000214576721},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4844000041484833},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.4772999882698059},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4359000027179718},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.3246000111103058}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6449999809265137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5789999961853027},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.51419997215271},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3962000012397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.390500009059906},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11334-025-00623-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11334-025-00623-3","pdf_url":null,"source":{"id":"https://openalex.org/S151239915","display_name":"Innovations in Systems and Software Engineering","issn_l":"1614-5046","issn":["1614-5046","1614-5054"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Innovations in Systems and Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11334-025-00623-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11334-025-00623-3","pdf_url":null,"source":{"id":"https://openalex.org/S151239915","display_name":"Innovations in Systems and Software Engineering","issn_l":"1614-5046","issn":["1614-5046","1614-5054"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Innovations in Systems and Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W409166618","https://openalex.org/W1985231403","https://openalex.org/W1995945562","https://openalex.org/W2037668591","https://openalex.org/W2063156085","https://openalex.org/W2094947835","https://openalex.org/W2125999269","https://openalex.org/W2151666086","https://openalex.org/W2348136092","https://openalex.org/W2474835145","https://openalex.org/W2536062280","https://openalex.org/W2548549162","https://openalex.org/W2786993482","https://openalex.org/W2906829543","https://openalex.org/W2963548617","https://openalex.org/W4236586490","https://openalex.org/W4250023757","https://openalex.org/W4318206478","https://openalex.org/W4385486483","https://openalex.org/W4401503494","https://openalex.org/W4404067039","https://openalex.org/W4404317222","https://openalex.org/W4405317570","https://openalex.org/W4409434089","https://openalex.org/W4412382140","https://openalex.org/W4414920038","https://openalex.org/W4415604006","https://openalex.org/W4416073306"],"related_works":[],"abstract_inverted_index":{"Software":[0],"fault":[1],"prediction":[2],"(SFP)":[3],"models":[4,49,200],"are":[5],"often":[6,205],"trained":[7,50],"on":[8,42,51,250],"severely":[9],"imbalanced":[10],"data.":[11],"Prior":[12],"work":[13],"also":[14,58],"warns":[15],"that":[16],"low":[17,203],"events\u2011per\u2011variable":[18],"(EPV)":[19],"ratios":[20,41],"can":[21],"yield":[22],"unstable":[23],"and":[24,31,38,45,72,118,123,136,185,220,242,244,253],"biased":[25],"estimates.":[26],"To":[27],"quantify":[28],"the":[29,43,146,164,168,174],"separate":[30],"joint":[32],"impact":[33,228],"of":[34,47,160,167],"(i)":[35,153],"class\u2011balancing":[36],"techniques":[37,85,209],"(ii)":[39,177],"EPV":[40,96,134,143,178,188,204,219],"accuracy":[44,184],"stability":[46,119,186],"SFP":[48],"five":[52,68,83],"real\u2011world,":[53],"open\u2011source":[54],"GitHub":[55,71],"projects.":[56],"We":[57,66,114,233],"examine":[59],"whether":[60],"classifier":[61,224],"choice":[62,195],"outweighs":[63],"either":[64],"factor.":[65],"extracted":[67],"projects":[69],"from":[70],"built":[73],"class\u2011level":[74],"datasets.":[75],"After":[76],"feature":[77],"selection":[78],"(genetic":[79],"algorithm),":[80],"we":[81],"evaluated":[82],"estimation":[84,199,208],"(PLS,":[86],"CART,":[87],"NB,":[88],"RF,":[89],"SVM)":[90],"under":[91],"a":[92,158,226,235],"factorial":[93],"design":[94],"crossing":[95],"\u2208":[97,101],"(1)":[98],"with":[99,149],"balancing":[100,131,169],"(None,":[102],"Up,":[103],"Down,":[104],"SMOTE,":[105],"ROSE)":[106],"[1].":[107],"AUC":[108,156],"is":[109,163,173],"used":[110],"to":[111],"measure":[112],"performance.":[113],"report":[115],"effect":[116],"sizes":[117],"(across":[120],"repeated":[121],"runs)":[122],"profile":[124],"computational":[125],"cost.":[126],"Baselines":[127],"include":[128],"(a)":[129],"no":[130],"at":[132,202,211],"each":[133],"level":[135],"(b)":[137],"an":[138,222,246],"additional":[139],"\u201craw\u201d":[140],"baseline":[141],"without":[142],"adjustment":[144],"for":[145],"only":[147],"dataset":[148],"non\u2011zero":[150],"defects":[151],"(Ceylon).":[152],"Balancing":[154],"improves":[155],"in":[157],"minority":[159],"settings;":[161],"SMOTE":[162],"most":[165],"reliable":[166],"methods,":[170],"whereas":[171],"ROSE":[172],"least":[175],"effective.":[176],"=":[179,189],"20":[180],"consistently":[181],"yields":[182],"higher":[183],"than":[187,229],"3":[190],"or":[191],"10.":[192],"(iii)":[193],"Classifier":[194],"matters":[196],"most:":[197],"strong":[198],"(RF/SVM)":[201],"outperform":[206],"weak":[207],"(PLS/CART)":[210],"high":[212],"EPV.":[213],"For":[214],"modern":[215],"GitHub\u2011based":[216],"SFP,":[217],"increasing":[218],"choosing":[221],"appropriate":[223],"have":[225],"greater":[227],"applying":[230],"generic":[231],"class\u2011balancing.":[232],"provide":[234],"reproducible":[236],"protocol":[237],"(data":[238],"processing":[239],"pipeline,":[240],"seeds,":[241],"scripts)":[243],"outline":[245],"external":[247],"validation":[248],"plan":[249],"NASA,":[251],"PROMISE,":[252],"Relink.":[254]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-25T00:00:00"}
