[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118108-en":3,"doc-seo-118108-105":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},118108,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Agile-based Requirements Engineering for Machine Learning - A Case Study on Personalized Nutrition","Requirements engineering is essential for building machine learning systems because it sets the basis for successful delivery, yet transferring practices from traditional software to ML introduces new difficulties. Static specification logic is replaced by data-driven logic, making correctness depend on learned behavior rather than code structure. This paper proposes an agile requirements engineering case study that uses user stories and acceptance criteria to define ML requirements, including data needs and validation via model interpretability for explainability and dataset quality metrics. A personalized nutrition and physical activity case study demonstrates the suitability of these artifacts for specifying and validating ML behavior.","Agile-based Requirements Engineering for Machine Learning: A Case  \nStudy on Personalized Nutrition  \nCarlos Cunha*1, Rafael Oliveira2, Rui Duarte3  \nSubmitted: 18/09/2023 Revised: 19/11/2023 Accepted: 29/11/2023  \nAbstract: Requirements engineering is crucial in developing machine learning systems, as it establishes the foundation for successful project execution. Nevertheless, incorporating requirements engineering approaches from traditional software engineering into machine learning projects presents new challenges. These challenges arise from replacing the software logic derived from static software specifications with dynamic software logic derived from data. This paper presents a case study exploring an agile requirement engineering approach popular in traditional software projects to specify requirements in machine learning software. These requirements allow reasoning about the correctness of software and design tests for validation. The absence of software specification in machine learning software is offset by employing data quality metrics, which are assessed using cutting-edge methods for model interpretability. A case study on personalized nutrition and physical activity demonstrated the adequacy of user stories and acceptance criteria format, popular in agile projects, for specifying requirements in the machine learning domain.  \nKeywords: requirements engineering, machine learning, deep learning, explainability, agile, user stories, acceptance criteria  \n1. Introduction  \nThe requirements engineering (RE) field presents distinct challenges regarding machine learning (ML) systems, which are not encountered in traditional information system development. Non-functional requirements elicitation and quality assurance of machine learning models and applications are a few examples.  \nSoftware engineers should understand ML performance measures to specify reasonable functional requirements, know quality requirements such as explainability, and integrate ML specifics in the RE process [1] . ML should also prioritize its validation process, particularly concerning RE, rather than solely focusing on verification, which examines whether the model has learned the correct specifications. Validation may determine whether the acquired behavior of an ML-based system is erroneous, even though the learning algorithm is implemented accurately.  \nUser stories and acceptance criteria are popular software engineering artifacts for requirements specification [2] . Acceptance criteria for ML models play a crucial role in evaluating their performance and determining their suitability for deployment. These criteria are benchmarks against which the model predictions or classifications are measured, providing a quantitative or qualitative assessment  \n1 Polytechnic Institute of Viseu, Portugal ORCID ID : 0000-0002-2754-5401  \n2 Polytechnic Institute of Viseu, Portugal  \n3 Polytechnic Institute of Viseu, Portugal ORCID ID : 0000-0002-6819-0985  \n* Corresponding Author Email: [cacunha@estgv.ipv.pt](cacunha@estgv.ipv.pt)  \nof effectiveness. Additionally, they can specify data requirements to validate the quality of datasets used to define the system behavior.  \nCurrent research on ML systems must integrate with existing RE methodologies and tools [3] . One reason is the impact of ML uncertainty on requirements engineering methods. Previous solutions address ML uncertainty using goal-oriented requirements analysis (GORE) [4] or represent requirements as ML metamodels for describing the environment, system state and data, the ML behaviors, and the learning behavior [5] . There is a research gap covering the specification of ML requirements using conventional agile artifacts that stakeholders can interpret and validate. Data requirements are the core of requirements specification since they compromised the system correctness but only became available in production. Hence, datasets are system inputs that require validation because they change over","cbCaib7AN2puEBvB","https://ap.wps.com/l/cbCaib7AN2puEBvB","pdf",425991,1,10,"English","en",105,"# Introduction\n## Requirements engineering challenges in machine learning\n## Validation vs. verification and explainability\n## Agile artifacts for ML requirements\n# Related Work\n## Mapping traditional RE to ML requirements\n## Validation and testing approaches for ML requirements\n# Case Study Structure\n## Problem definition and ML requirements\n## Results discussion\n## Conclusions and future work","[{\"question\":\"Why is requirements engineering different for machine learning systems compared with traditional software?\",\"answer\":\"Machine learning requirements must handle data-driven behavior rather than static specification-derived logic. This changes how functional and non-functional needs are elicited and how quality assurance is performed for models and applications.\"},{\"question\":\"How does the paper adapt agile requirements artifacts for machine learning?\",\"answer\":\"It uses user stories and acceptance criteria as interpretable artifacts for specifying ML requirements. Acceptance criteria support evaluating model performance and defining data requirements for validation.\"},{\"question\":\"What role do data quality metrics and model interpretability play in validation?\",\"answer\":\"The approach offsets the lack of traditional software specifications in ML by using data quality metrics and cutting-edge model interpretability methods. Together, they support assessing correctness and designing tests for validating effectiveness and suitability for deployment.\"}]","Agile-based Requirements Engineering for Machine Learning - A Case Study on Personalized Nutrition | PDF",1785681659,25,{"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},"agile-based-requirements-engineering-for-machine-learning-a-case-study-on-personalized-nutrition","",{"@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/agile-based-requirements-engineering-for-machine-learning-a-case-study-on-personalized-nutrition/118108/",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","2026-08-02",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},"Why is requirements engineering different for machine learning systems compared with traditional software?","Question",{"text":75,"@type":76},"Machine learning requirements must handle data-driven behavior rather than static specification-derived logic. This changes how functional and non-functional needs are elicited and how quality assurance is performed for models and applications.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper adapt agile requirements artifacts for machine learning?",{"text":80,"@type":76},"It uses user stories and acceptance criteria as interpretable artifacts for specifying ML requirements. Acceptance criteria support evaluating model performance and defining data requirements for validation.",{"name":82,"@type":73,"acceptedAnswer":83},"What role do data quality metrics and model interpretability play in validation?",{"text":84,"@type":76},"The approach offsets the lack of traditional software specifications in ML by using data quality metrics and cutting-edge model interpretability methods. Together, they support assessing correctness and designing tests for validating effectiveness and suitability for deployment.","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"]