Statistical Research Analyst State University of New York at Binghamton Vestal, New York, United States
Session Abstract: This study explores student success in terms of retention and graduation rates at the course level using data science and machine learning, an important topic in higher education. A case study from Binghamton University demonstrates how predictive models identified course combinations that promote success (GPA ≥ 3.0). Key insights include identifying high-risk courses and departments where students face challenges. Recommendations include interventions like interdisciplinary learning communities, curriculum adjustments, and early alert systems. This session is ideal for those seeking to apply data-driven insights to improve academic outcomes, enhance retention, and foster continuous improvement. Participants will gain practical tools and strategies to implement these methods at their institutions.
Objectives: (1) apply predictive models to identify course combinations improving student outcomes and high-risk areas and (2) explore actionable intervention strategies to support success.
