<![CDATA[Hybrid universities increasingly rely on learning management systems, advising platforms, and digital engagement records to understand student progress, yet the educational value of learning analytics depends on whether data are translated into timely, equitable, and human-centered support. First-year retention is an urgent problem because early withdrawal often reflects not only academic difficulty but also belonging, financial pressure, digital access, advising gaps, and institutional responsiveness. This article develops and illustrates an equity-oriented learning analytics model for first-year retention in hybrid universities. The model integrates predictive risk identification, advising outreach, instructor feedback, student-facing dashboards, and equity audits. Using a mixed-methods quasi-experimental design, the model study involved 1,248 first-year students across hybrid gateway courses. Students in the intervention cohort received analytics-informed outreach, structured advisor follow-up, and student-facing progress guidance, while the comparison cohort received standard advising support. Published evidence shows that national first-year persistence and retention remain uneven, with the National Student Clearinghouse reporting 76.5 percent persistence and 68.2 percent same-institution retention for fall 2022 starters, while retention remains lower for Hispanic, Black, and Native American students. The simulated results show improved retention, course completion, and early help-seeking in the intervention cohort, with the strongest gains among students who received advisor contact within seven days of risk identification. The article argues that learning analytics should be evaluated not by prediction accuracy alone but by its capacity to trigger fair, explainable, and relational support.]]>
Copyrights © 2026
