{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:14:53Z","timestamp":1778778893290,"version":"3.51.4"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information and Software Technology"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.infsof.2026.108156","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T23:34:28Z","timestamp":1777073668000},"page":"108156","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Architecting data-intensive applications: From architectural design to data quality"],"prefix":"10.1016","volume":"196","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4946-6269","authenticated-orcid":false,"given":"Moamin","family":"Abughazala","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Sharaf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6365-6515","authenticated-orcid":false,"given":"Henry","family":"Muccini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.infsof.2026.108156_b1","series-title":"Big Data: A Revolution That Will Transform How We Live, Work, and Think","author":"John Walker","year":"2014"},{"key":"10.1016\/j.infsof.2026.108156_b2","series-title":"Top 26 Twitter (x) statistics that we think you should know about","author":"charle","year":"2025"},{"key":"10.1016\/j.infsof.2026.108156_b3","series-title":"Volume of data\/information created, captured, copied, and consumed worldwide from 2010 to 2023, with forecasts from 2024 to 2028","author":"statista","year":"2024"},{"key":"10.1016\/j.infsof.2026.108156_b4","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.jnca.2016.08.002","article-title":"Data quality in internet of things: A state-of-the-art survey","volume":"73","author":"Karkouch","year":"2016","journal-title":"J. Netw. Comput. Appl."},{"issue":"22","key":"10.1016\/j.infsof.2026.108156_b5","doi-asserted-by":"crossref","first-page":"8052","DOI":"10.3390\/app10228052","article-title":"Quality assurance technologies of big data applications: A systematic literature review","volume":"10","author":"Ji","year":"2020","journal-title":"Appl. Sci."},{"key":"10.1016\/j.infsof.2026.108156_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2023.111855","article-title":"Data pipeline quality: Influencing factors, root causes of data-related issues, and processing problem areas for developers","volume":"207","author":"Foidl","year":"2024","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.infsof.2026.108156_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2020.110869","article-title":"ACCORDANT: A domain specific-model and DevOps approach for big data analytics architectures","volume":"172","author":"Castellanos","year":"2021","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.infsof.2026.108156_b8","series-title":"2010 Seventh Web Information Systems and Applications Conference","first-page":"106","article-title":"A data storage architecture supporting multi-level customization for saas","author":"Zheng","year":"2010"},{"key":"10.1016\/j.infsof.2026.108156_b9","series-title":"Data Architecture (Second Edition)","first-page":"1","article-title":"Chapter 1.1 - An introduction to data architecture","author":"Inmon","year":"2019"},{"key":"10.1016\/j.infsof.2026.108156_b10","series-title":"DAMA-DMBOK: Data Management Body of Knowledge (2nd Edition)","author":"International","year":"2017"},{"key":"10.1016\/j.infsof.2026.108156_b11","series-title":"2022 International Conference on Electrical, Computer and Energy Technologies","first-page":"1","article-title":"Data architectures\u2019 evolution and protection","author":"Sinan","year":"2022"},{"issue":"2","key":"10.1016\/j.infsof.2026.108156_b12","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1145\/3299887.3299891","article-title":"Data lifecycle challenges in production machine learning: a survey","volume":"47","author":"Polyzotis","year":"2018","journal-title":"ACM SIGMOD Rec."},{"key":"10.1016\/j.infsof.2026.108156_b13","doi-asserted-by":"crossref","unstructured":"N. Polyzotis, S. Roy, S.E. Whang, M. Zinkevich, Data management challenges in production machine learning, in: Proceedings of the 2017 ACM International Conference on Management of Data, 2017, pp. 1723\u20131726.","DOI":"10.1145\/3035918.3054782"},{"key":"10.1016\/j.infsof.2026.108156_b14","series-title":"2019 IEEE\/ACM 41st International Conference on Software Engineering: Software Engineering in Practice","first-page":"291","article-title":"Software engineering for machine learning: A case study","author":"Amershi","year":"2019"},{"issue":"4","key":"10.1016\/j.infsof.2026.108156_b15","doi-asserted-by":"crossref","first-page":"3607","DOI":"10.14419\/ijet.v7i4.21742","article-title":"Data sources and ingestion big data layers: meta-modeling of key concepts and features","volume":"7","author":"Erraissi","year":"2018","journal-title":"Int. J. Eng. Technol."},{"key":"10.1016\/j.infsof.2026.108156_b16","series-title":"2019 8th International Conference on Modeling Simulation and Applied Optimization","first-page":"1","article-title":"A big data visualization layer meta-model proposition","author":"Erraissi","year":"2019"},{"key":"10.1016\/j.infsof.2026.108156_b17","series-title":"Big Data: Principles and Best Practices of Scalable Realtime Data Systems","author":"Warren","year":"2015"},{"key":"10.1016\/j.infsof.2026.108156_b18","series-title":"ISO\/IEC\/IEEE 42010:2022 Systems and Software Engineering \u2013 Architecture Description","author":"ISO\/IEC\/IEEE","year":"2022"},{"key":"10.1016\/j.infsof.2026.108156_b19","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.ins.2014.01.015","article-title":"Data-intensive applications, challenges, techniques and technologies: A survey on big data","volume":"275","author":"Chen","year":"2014","journal-title":"Inform. Sci."},{"key":"10.1016\/j.infsof.2026.108156_b20","series-title":"Designing Data-Intensive Applications","author":"Kleppmann","year":"2019"},{"key":"10.1016\/j.infsof.2026.108156_b21","series-title":"Software Architecture for Big Data and the Cloud","first-page":"253","article-title":"Chapter 14 - exploring the evolution of big data technologies","author":"Bonner","year":"2017"},{"key":"10.1016\/j.infsof.2026.108156_b22","first-page":"1","article-title":"Engineering ai systems: A research agenda","author":"Bosch","year":"2021","journal-title":"Artif. Intell. Parad. Smart Cyber-Phys. Syst."},{"key":"10.1016\/j.infsof.2026.108156_b23","series-title":"Data Architecture: A Primer for the Data Scientist: A Primer for the Data Scientist","author":"Inmon","year":"2019"},{"key":"10.1016\/j.infsof.2026.108156_b24","series-title":"Great expectations","author":"Great Expectations","year":"2021"},{"key":"10.1016\/j.infsof.2026.108156_b25","series-title":"2023 IEEE 20th International Conference on Software Architecture Companion","first-page":"284","article-title":"Modeling data analytics architecture for iot applications using dat","author":"Abughazala","year":"2023"},{"key":"10.1016\/j.infsof.2026.108156_b26","first-page":"528","article-title":"The goal question metric approach","author":"Caldiera","year":"1994","journal-title":"Encycl. Softw. Eng."},{"issue":"2","key":"10.1016\/j.infsof.2026.108156_b27","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1007\/s10586-019-02986-2","article-title":"The role of structured and unstructured data managing mechanisms in the internet of things","volume":"23","author":"Azad","year":"2020","journal-title":"Clust. Comput."},{"key":"10.1016\/j.infsof.2026.108156_b28","series-title":"2016 International Conference on Information Communication and Embedded Systems","first-page":"1","article-title":"A review of big data environment and its related technologies","author":"Mohammed","year":"2016"},{"key":"10.1016\/j.infsof.2026.108156_b29","first-page":"1629","article-title":"Big data: concepts, technologies and applications in the public sector","volume":"10","author":"Alexandru","year":"2016","journal-title":"Int. J. Comput. Electr. Autom. Control. Inf. Eng."},{"key":"10.1016\/j.infsof.2026.108156_b30","series-title":"2018 21st Saudi Computer Society National Computer Conference","first-page":"1","article-title":"Rise of big data\u2013Issues and challenges","author":"Alabdullah","year":"2018"},{"key":"10.1016\/j.infsof.2026.108156_b31","series-title":"Big Data: Concepts, Technology, and Architecture","author":"Balusamy","year":"2021"},{"key":"10.1016\/j.infsof.2026.108156_b32","series-title":"New Horizons for a Data-Driven Economy: A Roadmap for Usage and Exploitation of Big Data in Europe","author":"Cavanillas","year":"2016"},{"issue":"1","key":"10.1016\/j.infsof.2026.108156_b33","first-page":"1","article-title":"A meta-model for diverse data sources in business intelligence","volume":"7","author":"Kalna","year":"2019","journal-title":"Am. J. Embed. Syst. Appl."},{"key":"10.1016\/j.infsof.2026.108156_b34","series-title":"2016 Third International Conference on Systems of Collaboration (SysCo)","first-page":"1","article-title":"Data storage in big data context: A survey","author":"Elomari","year":"2016"},{"key":"10.1016\/j.infsof.2026.108156_b35","series-title":"2018 10th International Conference on Computational Intelligence and Communication Networks","first-page":"54","article-title":"Comparative analysis of GFS and HDFS: technology and architectural landscape","author":"Verma","year":"2018"},{"key":"10.1016\/j.infsof.2026.108156_b36","series-title":"Architectural software patterns for the development of IoT smart applications","author":"Borelli","year":"2020"},{"key":"10.1016\/j.infsof.2026.108156_b37","series-title":"2020 46th Euromicro Conference on Software Engineering and Advanced Applications","first-page":"13","article-title":"Modelling data pipelines","author":"Raj","year":"2020"},{"key":"10.1016\/j.infsof.2026.108156_b38","series-title":"Big Data Application Architecture Q & A","first-page":"9","article-title":"Big data application architecture","author":"Sawant","year":"2013"},{"key":"10.1016\/j.infsof.2026.108156_b39","series-title":"Data Pipelines Pocket Reference","author":"Densmore","year":"2021"},{"key":"10.1016\/j.infsof.2026.108156_b40","series-title":"The Internet of Things and Big Data Analytics: Integrated Platforms and Industry Use Cases","author":"Raj","year":"2020"},{"issue":"2","key":"10.1016\/j.infsof.2026.108156_b41","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1109\/TSC.2018.2816941","article-title":"Model-based big data analytics-as-a-service: take big data to the next level","volume":"14","author":"Ardagna","year":"2018","journal-title":"IEEE Trans. Serv. Comput."},{"key":"10.1016\/j.infsof.2026.108156_b42","article-title":"Big data quality dimensions: a systematic literature review","volume":"17","author":"Ramasamy","year":"2020","journal-title":"JISTEM-J. Inf. Syst. Technol. Manag."},{"key":"10.1016\/j.infsof.2026.108156_b43","doi-asserted-by":"crossref","DOI":"10.5334\/dsj-2015-002","article-title":"The challenges of data quality and data quality assessment in the big data era","volume":"14","author":"Cai","year":"2015","journal-title":"Data Sci. J."},{"issue":"63","key":"10.1016\/j.infsof.2026.108156_b44","article-title":"Data quality dimensions to ensure optimal data quality","volume":"20","author":"Jesi\u013cevska","year":"2017","journal-title":"Rom. Econ. J."},{"key":"10.1016\/j.infsof.2026.108156_b45","series-title":"2023 Fourth International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","first-page":"99","article-title":"Architecture description framework for data-intensive applications","author":"Abughazala","year":"2023"},{"key":"10.1016\/j.infsof.2026.108156_b46","series-title":"Component Software. Beyond Object Oriented Programming","author":"Szyperski","year":"1998"},{"key":"10.1016\/j.infsof.2026.108156_b47","series-title":"European Conference on Software Architecture","first-page":"90","article-title":"Dat: Data architecture modeling tool for data-driven applications","author":"Abughazala","year":"2022"},{"key":"10.1016\/j.infsof.2026.108156_b48","series-title":"Eclipse modeling framework","author":"Eclipse Foundation, Inc","year":"2009"},{"key":"10.1016\/j.infsof.2026.108156_b49","series-title":"Eclipse epsilon","author":"Eclipse Foundation, Inc","year":"2009"},{"key":"10.1016\/j.infsof.2026.108156_b50","series-title":"Graphical model editor development with eugenia\/GMF","author":"Eclipse Foundation, Inc","year":"2009"},{"key":"10.1016\/j.infsof.2026.108156_b51","first-page":"43","article-title":"Systematic mapping study of template-based code generation","volume":"52","author":"Syriani","year":"2018","journal-title":"Comput. Lang. Syst. Struct."},{"key":"10.1016\/j.infsof.2026.108156_b52","series-title":"EuroPLoP","first-page":"285","article-title":"A catalog of patterns for program generation","author":"Voelter","year":"2003"},{"key":"10.1016\/j.infsof.2026.108156_b53","first-page":"28","article-title":"Lakehouse: a new generation of open platforms that unify data warehousing and advanced analytics","volume":"vol. 8","author":"Armbrust","year":"2021"},{"issue":"12","key":"10.1016\/j.infsof.2026.108156_b54","doi-asserted-by":"crossref","first-page":"1986","DOI":"10.14778\/3352063.3352116","article-title":"Data lake management: challenges and opportunities","volume":"12","author":"Nargesian","year":"2019","journal-title":"Proc. VLDB Endow."},{"key":"10.1016\/j.infsof.2026.108156_b55","series-title":"Analysis of Data Warehouse Architectures: Modeling and Classification","author":"Yang","year":"2019"},{"key":"10.1016\/j.infsof.2026.108156_b56","doi-asserted-by":"crossref","unstructured":"M. Guerriero, S. Tajfar, D.A. Tamburri, E. Di Nitto, Towards a model-driven design tool for big data architectures, in: Proceedings of the 2nd International Workshop on BIG Data Software Engineering, 2016, pp. 37\u201343.","DOI":"10.1145\/2896825.2896835"},{"key":"10.1016\/j.infsof.2026.108156_b57","series-title":"2018 IEEE International Conference on Software Architecture","first-page":"156","article-title":"Infrastructure-as-code for data-intensive architectures: a model-driven development approach","author":"Artac","year":"2018"},{"key":"10.1016\/j.infsof.2026.108156_b58","doi-asserted-by":"crossref","first-page":"3577","DOI":"10.1007\/s10270-019-00730-3","article-title":"A UML profile for the design, quality assessment and deployment of data-intensive applications","volume":"18","author":"Perez-Palacin","year":"2019","journal-title":"Softw. Syst. Model."},{"key":"10.1016\/j.infsof.2026.108156_b59","doi-asserted-by":"crossref","first-page":"1032","DOI":"10.1016\/j.future.2017.07.033","article-title":"A performance modeling framework for lambda architecture based applications","volume":"86","author":"Gribaudo","year":"2018","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.infsof.2026.108156_b60","doi-asserted-by":"crossref","first-page":"169740","DOI":"10.1109\/ACCESS.2020.3024066","article-title":"Big data management and analytics metamodel for IoT-enabled smart buildings","volume":"8","author":"Bashir","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.infsof.2026.108156_b61","series-title":"2018 IEEE 4th International Conference on Collaboration and Internet Computing","first-page":"388","article-title":"Auditing and assessment of data traffic flows in an IoT architecture","author":"Nesi","year":"2018"},{"key":"10.1016\/j.infsof.2026.108156_b62","series-title":"International Conference on Product-Focused Software Process Improvement","first-page":"168","article-title":"Data pipeline management in practice: Challenges and opportunities","author":"Munappy","year":"2020"},{"key":"10.1016\/j.infsof.2026.108156_b63","doi-asserted-by":"crossref","DOI":"10.1109\/TSE.2023.3291003","article-title":"Dealing with data challenges when delivering data-intensive software solutions","author":"Graetsch","year":"2023","journal-title":"IEEE Trans. Softw. Eng."},{"key":"10.1016\/j.infsof.2026.108156_b64","series-title":"Data management challenges in agile software projects: A systematic literature review","author":"Fawzy","year":"2024"}],"container-title":["Information and Software Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095058492600145X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095058492600145X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:40:19Z","timestamp":1778776819000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095058492600145X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":64,"alternative-id":["S095058492600145X"],"URL":"https:\/\/doi.org\/10.1016\/j.infsof.2026.108156","relation":{},"ISSN":["0950-5849"],"issn-type":[{"value":"0950-5849","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Architecting data-intensive applications: From architectural design to data quality","name":"articletitle","label":"Article Title"},{"value":"Information and Software Technology","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.infsof.2026.108156","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"108156"}}