Open AccessImpact of Artificial Intelligence on Software Engineering Phases and Activities (2013-2024): A Quantitative Analysis Using Zero-Truncated Poisson Model
Author(s) -
Usman Khan Durrani,
Mustafa Akpinar,
Hakan Bektas,
Mohammad Saleh
Publication year - 2025
Publication title -
ieee access
Language(s) - English
Resource type - Magazines
SCImago Journal Rank - 0.587
H-Index - 127
eISSN - 2169-3536
DOI - 10.1109/access.2025.3574462
Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation
This paper presents the results of a quantitative analysis derived from data collected in our earlier systematic literature review, focusing on integrating Artificial Intelligence (AI) techniques across various phases of Software Engineering (SE). Employing a Zero-Truncated Poisson (ZTP) model, we analyzed 120 selected research papers to assess the impact of AI methodologies on SE phases. The findings indicate significant improvements attributable to AI in different phases of SE. Specifically, AI techniques have been found to enhance the accuracy of the planning, requirement engineering, and development phases and improve the efficiency of the requirement engineering and design phases. Notably, AI’s integration has markedly improved the accuracy and efficiency of the requirement engineering phase, underscoring AI’s critical role in advancing SE practices. This study contributes to a deeper understanding of the quantitative impact of AI on SE, providing valuable insights for practitioners and researchers in understanding AI technologies to enhance SE phases.