Session Abstract: Community colleges play a vital role in preparing students for transfer to four-year institutions and supporting baccalaureate degree completion. This discussion-based session, part of a broader transfer-student research project, analyzes data from the National Student Clearinghouse and a large metropolitan community college district spanning 10 years and nearly half a million students to explore factors influencing degree attainment after transfer. Discussion leaders will present four predictive models and their testing results before opening the floor to participants to explore challenges and solutions in data management, feature selection, model optimization, and effectively communicating findings to policymakers. The session aims to foster collaboration on best practices for designing, testing, and deploying predictive models to inform resource allocation and strategic planning for building students’ academic and personal capital, ultimately improving degree-completion rates.
Keywords: machine learning models, community college transfer, bachelor's degree completion, predictive analytics
