Recent research:
This body of work investigates how higher education systems, particularly at Salesian Polytechnic/Technical Universities in Ecuador, shape graduate outcomes, student success, and well-being through data-driven methods and innovative graduation mechanisms. Across studies, capstone-project-based graduation emerges as a predictor of stronger immediate employability and skill development, while traditional full-degree exams may correlate with longer-term unemployment in the field of study. The research extends to stressors in higher education, revealing how student performance interacts with faculty workload and institutional pressures, including a pandemic-era anomaly of higher grades amidst stress, underscoring the value of proactive data analytics for early intervention and well-being. Complementary work adds predictive Learning Analytics using socioeconomic data, revealing cohorts at academic risk beyond aptitude alone and employing machine learning to identify at-risk students. A learning recommender system based on collaborative filtering addresses information overload in optional subject selection, with dimensionality reduction mitigating data sparsity to improve recommendations. Additional studies connect exam-related anxiety to performance, highlighting the impact of terminology and stress management on academic outcomes. Overall, the methodological core spans data mining, machine learning, learning analytics, and data-driven policy recommendations to enhance employability, success, and well-being in higher education environments.

Key Topics:

• Education, Pedagogy, Teacher Training & Inclusion
• Educational Technology, Gamification, XR & Learning Analytics
• Research Methods, Measurement, Bibliometrics & Academic Practice
• Artificial Intelligence, Machine Learning & Data Science
• Psychology, Mental Health, Social Well-being & Violence Prevention