This research is like having a smart assistant look at years of student records and tell you, “These are the few things that really matter for whether bioengineering students actually master the skills you care about.” It tests different machine learning models on student data to discover which factors (attendance, prior grades, course activities, etc.) best predict whether students will achieve required competencies.
Universities struggle to know early which students are at risk of not achieving core competencies and which levers (teaching strategies, assessments, behaviors) truly drive competency mastery. This work uses machine learning to pinpoint the most important predictors so educators can intervene earlier and redesign curricula and assessments more effectively.
Classical-ML (Scikit/XGBoost)
Structured SQL
Medium (Integration logic)
Data availability and labeling quality (sufficient, clean, longitudinal student performance and competency labels per program)
Early Adopters
Focuses narrowly on competency-based achievement in a bioengineering program, using multiple machine learning models to both predict outcomes and identify key predictive features, which gives program-level, actionable insights rather than generic student performance analytics.