Industrial Automatic Control Systems and Controllers Annotation << Back Systematic Review of Machine Learning Integration in Software Design Pattern Detection for SDLC Jameleh Asaad Asaad, Dzhulay E.V., Аvksentieva E.Yu. This article presents a systematic review of existing research on the intersection between machine learning (ML) and software design pattern detection, with a focus on their integration within the software development life cycle (SDLC). Drawing on prior literature, we examine the role of ML techniques in enhancing pattern recognition across various SDLC stages, including requirement analysis, design, implementation, testing, and maintenance. We analyze key methods, categorize detection approaches, and identify current gaps in reproducibility, evaluation, and practical implementation. Based on the fi ndings, we propose a conceptual framework that outlines how ML-driven pattern detection can be systematically applied in software engineering practice. The study concludes with recommendations for future research directions that emphasize scalable solutions and industry adoption. Keywords: machine learning, design pattern detection, software development life cycle, software engineering, systematic review, requirement analysis, software testing. DOI: 10.25791/asu.8.2025.1606 Pp. 45-51.