[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126336-en":3,"doc-seo-126336-105":30,"detail-sidebar-cat-0-en-105":92},{"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":11,"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},126336,962085570644,"Evangeline","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Comparing machine learning techniques for software requirements risk prediction - A comparative study","Software requirements are a critical phase for documenting, eliciting, and maintaining stakeholder needs, yet risks in the SDLC can cause delays, cost overruns, and even project failure. Risk identification and analysis are often performed manually, introducing bias and inconsistent evaluations. This study compares logistic regression, multilayer perceptron, support vector machine, decision tree, naive Bayes, and random forest models using cross-validation and k-fold training, then evaluates precision, accuracy, and recall. Statistical testing identifies which techniques best predict software requirements risk levels.","Comparing machine learning techniques for software requirements risk prediction  \nYasiel Pérez Vera, Álvaro Fernández Del Carpio  \nDepartment of Software Engineering, Universidad La Salle, Arequipa, Perú  \nArticle history:  \nReceived Dec 13, 2023 Revised Jan 14, 2024 Accepted Jan 16, 2024  \nKeywords:  \nClassification techniques Comparative analysis Evaluation metrics Machine learning  \nRisk prediction Software requirements  \nCorresponding Author:  \nSoftware requirements are the most critical phase focused on documenting, eliciting, and maintaining the stakeholders’ requirements. Risk identification and analysis are preemptive actions designed to anticipate and prepare for potential issues. Usually, this classification of risks is done manually, a practice that the personal judgment of the risk analyst or the project manager might influence. Machine learning (ML) techniques were proposed to predict the risk level in software requirements. The techniques used were logistic regression (LR), multilayer perceptron (MLP) neural network, support vector machine (SVM), decision tree (DT), naive bayes, and random forest (RF) . Each model was trained and tested using cross-validation with k-folds, each with its respective parameters, to provide optimal results. Finally, they were compared based on precision, accuracy, and recall metrics. Statistical tests were performed to determine if there were significant differences between the different ML techniques used to classify risks. The results concluded that the DT and RF are the techniques that best predict the risk level in software requirements.  \nThis is an open access article under the CC BY-SA license.  \nYasiel Pérez Vera  \nDepartment of Software Engineering, Universidad La Salle Alfonso Ugarte Avenue, Arequipa, Perú [Email: yperez@ulasalle.edu.pe](Email: yperez@ulasalle.edu.pe)  \nArticle Info ABSTRACT  \n1. INTRODUCTION  \nSoftware development involves a group of interconnected activities ranging from planning where the objectives and scope of the project are established, specification of requirements to determine the needs and expectations of the users, conceptualization of the solution through the design, writing the source code, and finally deployment and maintenance to ensure the availability of the solution, up-to-date and free of errors. Software requirements are the most critical phase focused on documenting, eliciting, and keeping the stakeholders’necessities [1] . Frequently, successfully discussing and securing stakeholders’ main requisites is a critical factor in creating a high-quality software system [2]. However, in the software development life cycle (SDLC), there is a risk of imprecise processes that can lead to the potential failure of the software. These alarming processes are called software risks. If these risks are not identified in time, it may lead to project failure [3].  \nThe standish group report [4] has continually pointed out the software industry’s frequent high failure rates. The report said that only 16.2% of projects were successful, completed on time and budget, and had all expected features. Most projects (approximately 52.7%) exceeded budget, missed deadlines, and missed some promised features. This results in 31.1% of projects being categorized as failures, indicating they were either abandoned or canceled. Some factors influencing whether a project succeeds or fails include executive engagement, precise requirement definitions, efficient project management, and active involvement of the end user.  \nRisk identification and analysis are preemptive actions designed to anticipate and prepare for potential issues. It implies identifying potential risks, evaluating their likely impact and frequency, and formulating strategies for mitigation or contingency plans to tackle them proactively [5] . Risks can be categorized using different criteria, including their origin, type, or impact on the project [6] . Usually, this classification of risks is done manual","cbCaitgTEixBlHvc","https://ap.wps.com/l/cbCaitgTEixBlHvc","pdf",623998,1,12,"English","en",105,"# 1. INTRODUCTION\n## Software requirements and software risks\n## Manual risk classification and its limitations\n## Motivation for machine learning\n# 2. MATERIALS AND METHODS\n## Materials and methods used","[{\"question\":\"Why is risk prediction important in software requirements?\",\"answer\":\"Software risks can lead to imprecise processes and potential failure. If misunderstood or poorly managed requirements are not identified early, the project may face delays, cost overruns, or failure.\"},{\"question\":\"Which machine learning techniques are compared in the study?\",\"answer\":\"The study compares logistic regression, multilayer perceptron neural network, support vector machine, decision tree, naive Bayes, and random forest models.\"},{\"question\":\"How are the models evaluated and compared?\",\"answer\":\"Models are trained and tested using cross-validation with k-folds. Results are compared using precision, accuracy, and recall metrics, followed by statistical tests to check significant differences.\"}]","Comparing machine learning techniques for software requirements risk prediction - A comparative study | PDF",1785904534,30,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"comparing-machine-learning-techniques-for-software-requirements-risk-prediction-a-comparative-study","",{"@graph":36,"@context":86},[37,54,69],{"@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/comparing-machine-learning-techniques-for-software-requirements-risk-prediction-a-comparative-study/126336/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is risk prediction important in software requirements?","Question",{"text":76,"@type":77},"Software risks can lead to imprecise processes and potential failure. If misunderstood or poorly managed requirements are not identified early, the project may face delays, cost overruns, or failure.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning techniques are compared in the study?",{"text":81,"@type":77},"The study compares logistic regression, multilayer perceptron neural network, support vector machine, decision tree, naive Bayes, and random forest models.",{"name":83,"@type":74,"acceptedAnswer":84},"How are the models evaluated and compared?",{"text":85,"@type":77},"Models are trained and tested using cross-validation with k-folds. Results are compared using precision, accuracy, and recall metrics, followed by statistical tests to check significant differences.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":122},"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":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]