Maria Santos, Kwok-Wai Cheung

In the field of Education, Educational Technology and Digital Pedagogy, delayed identification of struggling students leads to high first-year university course dropout and attrition rates. This empirical investigation systematically examines Learning Analytics Dashboards for Early Prediction of Academic Underperformance in Blended University Courses through a multi-stage experimental methodology and rigorous quantitative analytical framework. Utilizing random forest and logistic regression models trained on LMS log telemetry and clickstream data from 3,500 undergraduates, data were gathered across multiple operational cycles and validated against established international benchmarks. The statistical and computational results reveal that the predictive model identified at-risk students with 87% sensitivity by week four of the semester, enabling timely advising interventions. Comparative sensitivity analyses confirmed a statistically significant improvement (p < 0.01) over conventional baseline approaches, with heightened reproducibility and robust fault tolerance. These comprehensive findings provide actionable theoretical insights and practical implementation guidelines for university academic advising services and student retention administrators. Furthermore, the standardized protocols established in this study offer a valuable foundation for future cross-disciplinary investigations, policy formulation, and scalable technological deployment across global academic and industrial environments.