[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119296-en":3,"doc-seo-119296-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119296,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Evaluation of Machine Learning Algorithms on Software Fault Estimation (SFE)","Software Fault Estimation (SFE) aims to support the development of error-free, cost-friendly software by predicting defect-prone modules. This study evaluates eight machine learning algorithms—LSTM, KNN, RNN, GNN, MLP, Naïve Bayes, Random Forest, and Entropy (with logistic regression)—on the PROMISE dataset. Performance is measured using recall, accuracy, and precision. Results indicate MLP and LSTM achieve stronger precision, accuracy, and recall than the other methods, with LSTM reporting 0.83 precision, 0.85 accuracy, and 0.8 recall.","Keywords: Machine Learning, KNN, Software Fault Estimation (SEF), LSTM, MLP, GNN, Software Engineering,  \nSoftware Errors.  \nJournal Info:  \nSubmitted: December 01, 2024 Accepted:  \nDecember 22, 2024 Published:  \nDecember 31, 2024  \nEvaluation of Machine Learning Algorithmson Software Fault Estimation (SFE)  \nFaria Nazir 1 , Hareem Aslam 1  \n1 Department of Software Engineering, University of Management and Technology, Lahore, Pakistan  \nAbstract  \nSoftware Fault Estimation (SFE) approaches are being utilized to develop error free and cost friendly software. In this regard, machine learning algorithms are utilized to efficiently estimate the faults in the software. In this study, we implement eight machine learning based algorithms such as Long Short Term Memory networks (LSTM), K-Nearest Neighbors (KNN), Recurrent Neural networks (RNN), Graph Neural Network (GNN), Multi Layer Perception (MLP), Naïve Bayes, Random Forest, and Entropy using logistic regression model. All the algorithms are applied to the promise dataset for performance evaluation based on performance benchmarks such as recall, accuracy, and precision. MLP and LSTM algorithms showed promising results as compared to the other algorithms in terms of precision, accuracy, and recall. LSTM showed 0.83,0.85, and 0.8% precision, accuracy,and recall, respectively whereas RNN showed 0.79%, 0.60, and 0.79% recall, precision, and accuracy, respectively.  \n*Correspondence author email address: [nosheen.qamar@umt.edu.pk](nosheen.qamar@umt.edu.pk)[ ](nosheen.qamar@umt.edu.pk)DOI: 10.21015/vtse.v12i4 .2036  \n1. Introduction  \nThe use of computer systems has escalated over the last 20 years in almost every aspect of human life [1] . Complex software systems are being developed to digitalize the conventional processes involved in our daily lives. This digitalization transformed traditional procedures into automated processes, consequently making our lives easier and more comfortable than ever. However, the complexity of these automated procedures paves the way for uncertainty, which can  \nbe a cause of invalid and unwanted outcomes. To overcome this issue, Software Fault Estimation (SFE) approaches are being utilized to develop error-free and cost-friendly software. Researchers are further exploring this innovative domain for the better prediction of defect-prone modules.  \nIn general, a software defect can be classified asa software error, software fault or a software failure [2] . A software defect is defined as the invalid state of the software that does not conform to the quality requirements or standards required by the end-users or  \nThis work is licensed under a Creative Commons Attribution 3.0 License.  \nVFAST Transactions on Software Engineering Volume 12, Issue 4, 2024  \nclients [4] . It is quite common that software defects occur due to the errors caused by developers, or the architectural issues neglected by software architects during the software development life cycle. Software defects can further be categorized as mathematical defects that occur due to the limited domain knowledge of the programmer about that mathematical expression. Syntax defects occur due to the unfamiliarity of the developer with the programming language used in the development of the software. Logical defects that occur due to the false or partial understanding of the problem by the developer. Interface defects that negatively impact the usability of the software and harm the end-user experience. Performance defects that result in undesirable and unwanted outcomes from the software [5] .  \nResearch Gap:  \nThe need for effective software fault estimation (SFE) is critically important due to its huge impact on software development costs. It can be reduced by avoiding the number of faults which can arise in the future [6] . SFE can efficiently point out the error-prone modules in software.Once defect-prone modules are detected, resources can be utilized to deal with these flawed modules on apriority ba","cbCaiopigMz0JOl2","https://ap.wps.com/l/cbCaiopigMz0JOl2","pdf",196914,1,10,"English","en",105,"# Introduction\n## Research Gap\n## Research Objective\n## Research Contribution","[{\"question\":\"What problem does Software Fault Estimation (SFE) address?\",\"answer\":\"SFE helps predict defect-prone modules so software projects can reduce faults early, lowering quality assurance cost and improving reliability.\"},{\"question\":\"Which machine learning algorithms are evaluated in the study?\",\"answer\":\"The study evaluates LSTM, KNN, RNN, GNN, MLP, Naïve Bayes, Random Forest, and Entropy methods (with a logistic regression model).\"},{\"question\":\"How is the model performance evaluated?\",\"answer\":\"Performance is benchmarked using recall, accuracy, and precision on the PROMISE dataset.\"}]","Evaluation of Machine Learning Algorithms on Software Fault Estimation (SFE) | PDF",1785723571,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"evaluation-of-machine-learning-algorithms-on-software-fault-estimation-sfe","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/evaluation-of-machine-learning-algorithms-on-software-fault-estimation-sfe/119296/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Software Fault Estimation (SFE) address?","Question",{"text":75,"@type":76},"SFE helps predict defect-prone modules so software projects can reduce faults early, lowering quality assurance cost and improving reliability.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning algorithms are evaluated in the study?",{"text":80,"@type":76},"The study evaluates LSTM, KNN, RNN, GNN, MLP, Naïve Bayes, Random Forest, and Entropy methods (with a logistic regression model).",{"name":82,"@type":73,"acceptedAnswer":83},"How is the model performance evaluated?",{"text":84,"@type":76},"Performance is benchmarked using recall, accuracy, and precision on the PROMISE dataset.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]