<![CDATA[The rapid adoption of hybrid learning in higher education has generated extensive educational data, creating opportunities to enhance teaching and learning through Learning Analytics Dashboards (LADs). By integrating data visualization and predictive analytics, LADs enable institutions to monitor student engagement, identify academically at-risk students, and support timely instructional interventions. However, existing research remains fragmented across learning analytics, machine learning, and dashboard design, limiting a comprehensive understanding of their role in predicting student learning outcomes. This study aims to systematically synthesize current evidence on the implementation of Learning Analytics Dashboards in hybrid higher education. A Systematic Literature Review (SLR) was conducted following the PRISMA 2020 guidelines. Relevant studies published between 2020 and 2026 were identified from Scopus, Web of Science, ScienceDirect, SpringerLink, and IEEE Xplore using predefined inclusion and exclusion criteria. The selected studies were analyzed through qualitative thematic synthesis to examine publication trends, predictive algorithms, learning indicators, dashboard functionalities, educational impacts, implementation challenges, and future research directions. The findings indicate that Learning Analytics Dashboards have evolved into strategic decision-support systems by integrating multidimensional learning data with machine learning techniques to improve early identification of at-risk students and support evidence-based instructional decisions. Nevertheless, challenges related to data quality, interoperability, ethical governance, explainability, and institutional readiness remain significant. This review provides an integrated perspective and practical recommendations for developing transparent, intelligent, and learner-centered predictive analytics systems in higher education.]]>
