This work is like putting a ‘Fitbit’ on a blended learning master’s program: it tracks different aspects of students’ experience (online and in-person) and then uses data analytics to see which factors are most strongly linked to their grades.
Universities run blended postgraduate programs without clear, data-backed insight into which parts of the student experience (e.g., online tools, teaching methods, support services, workload, assessment design) actually drive academic success. This research uses analytics to identify which experiences matter most for performance, so institutions can redesign courses and support systems more effectively.
Domain-specific educational data and survey instruments capturing nuanced aspects of UK postgraduate blended learning, plus analytic know‑how on linking these to performance outcomes.
Classical-ML (Scikit/XGBoost)
Structured SQL
Medium (Integration logic)
Data access and quality—collecting clean, consistent, and privacy‑compliant student experience and performance data at scale.
Early Majority
Focus on UK postgraduate students in blended learning with an explicit, data-analytic linkage between detailed experience measures and academic performance, rather than generic satisfaction analytics or undergrad-only studies.
126 use cases in this application