<![CDATA[This study aims to systematically review the application of machine learning-based clustering algorithms in the evaluation of Graduate Learning Outcomes (CPL) in higher education. The review was conducted using the PRISMA approach on articles published in the Scopus database during the period 2020–2025. A total of 52 articles were analyzed to identify trends in the algorithms used, implementation challenges, and their contributions to curriculum development. The findings show that algorithms such as K-Means, Hierarchical Clustering, and Fuzzy C-Means are frequently used in mapping student competencies. However, their implementation in practice remains limited due to insufficient model validation, lack of justification for algorithm selection, and a disconnect between analytical results and academic decision-making. This situation reflects a broader issue in the integration of machine learning into educational contexts, where the technical potential of algorithms has not yet been fully translated into meaningful pedagogical impact. As a conceptual contribution, this study develops a machine learning-based computational model that includes the stages of CPL data collection, preprocessing, cluster modeling, result evaluation, and integration into curriculum policy. The proposed model is designed to enhance transparency, adaptability, and evidence-based decision-making in curriculum management systems. This study also highlights the need for the development of soft clustering techniques, integration with digital learning systems, and attention to the ethics and transparency of algorithms in data-based evaluation. Thus, this study emphasizes the importance of bridging the gap between algorithmic analysis and applicable educational strategies within higher education institutions.]]>
