Recent research:
The research focuses on leveraging learning analytics and data mining to optimize higher education ecosystems, with a particular emphasis on student success, academic performance, and institutional decision-making. By integrating machine learning techniques, such as collaborative filtering and matrix factorization, the work addresses challenges like data sparsity in recommender systems for course selection and the identification of at-risk student cohorts through socioeconomic and academic variable analysis. A significant portion of the research investigates the intersection of cognitive psychology and education, specifically examining metacognitive illusions, the impact of exam-induced stress on cognitive performance, and the role of instructional media in shaping self-perceived versus actual mastery. Furthermore, the studies evaluate institutional practices, such as graduation modalities, demonstrating that project-based learning enhances employability compared to traditional examination methods. By analyzing long-term institutional data, the research provides a framework for understanding how systemic disruptions, such as the COVID-19 pandemic, influence the relationship between faculty well-being, grading practices, and student outcomes, ultimately advocating for data-driven strategies to improve educational quality and sustainability.

Key Topics:

• Learning analytics and educational data mining
• Student success prediction and risk assessment
• Cognitive biases and metacognitive illusion in learning
• Higher education employability and graduation modalities
• Recommender systems for academic course selection
• Impact of stress and anxiety on academic performance