EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Driven Dynamic Requirement Prioritization in Agile Product Backlogs Using the AISA Framework

Muhammad Arslan, Sidra Yousaf Khan, Dilawar Hussain, Nadeem Rasool, Maham Amin, Dr. Ahmad Kahloon

The Critical Review of Social Sciences Studies · 30.03.2026 · 4 (1) · 7826-7838

DOI: 10.59075/gntyy367 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Critical Review of Social Sciences Studies, online erschienen am 30.03.2026. Verfasst von Muhammad Arslan und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agile software development demands continuous, accurate, and adaptive requirement prioritization. Traditional static methods such as MoSCoW and Kano models fail to accommodate real-time stakeholder dynamics, redundant requirements, and evolving business contexts. This study addresses the research question: How can AI techniques enhance the accuracy and adaptability of requirement prioritization in Agile environments using structured elicitation approaches? This paper proposes the AISA (Accurate, Inclusive, Structured, Adaptive) framework, a hybrid methodology that integrates multi-perspective Viewpoints Grid Elicitation with Artificial Intelligence (AI)-driven analysis, including Natural Language Processing (NLP), sentiment analysis, and dynamic scoring algorithms. The redundancy-detection and Dynamic Demand Prioritization (DDP) components were evaluated on 138 real-world requirements drawn from two domain case studies (healthcare/clinical program administration and consumer e-commerce, sourced from the public PROMISE NFR benchmark dataset): the pipeline flagged 3 near-duplicate requirement pairs, reprioritized 81.9% of requirements relative to a static equal-weighted baseline, and maintained a mean rank correlation of 0.957 with that baseline, showing that AISA's sentiment- and dependency-aware scoring produces materially different, targeted prioritization outcomes on authentic requirement text. Stakeholder-facing outcomes (satisfaction, sprint velocity, and qualitative acceptance) are addressed by a planned human-subject validation study described in Section V.

Zitieren

APA

Arslan, M., Khan, S. Y., Hussain, D., Rasool, N., Amin, M., & Kahloon, D. A. (2026). AI-Driven Dynamic Requirement Prioritization in Agile Product Backlogs Using the AISA Framework. The Critical Review of Social Sciences Studies, 4(1), 7826-7838. https://doi.org/10.59075/gntyy367

Vancouver

Arslan M, Khan SY, Hussain D, Rasool N, Amin M, Kahloon DA. AI-Driven Dynamic Requirement Prioritization in Agile Product Backlogs Using the AISA Framework. The Critical Review of Social Sciences Studies. 2026;4(1):7826-7838. doi:10.59075/gntyy367

BibTeX
@article{Arslan2026,
  author = {Arslan, Muhammad and Khan, Sidra Yousaf and Hussain, Dilawar and Rasool, Nadeem and Amin, Maham and Kahloon, Dr. Ahmad},
  title = {AI-Driven Dynamic Requirement Prioritization in Agile Product Backlogs Using the AISA Framework},
  journal = {The Critical Review of Social Sciences Studies},
  year = {2026},
  volume = {4},
  number = {1},
  pages = {7826--7838},
  doi = {10.59075/gntyy367}
}
Kostenlos starten →