Building a College Recommendation Engine for NCSA Student Athletes

The CR system matches student-athletes with suitable college sports programs by analyzing students’ characteristics and preferences which are then used to identify programs that best align with them. Our analysis shows that our recommendation system accurately predicts the school a student actually committed to 33% of the time, significantly outperforming random guessing (0.5%) and a benchmark model (12%). Implementing the CR system will ease the burden on recruiting coaches, and provide students with immediate, personalized program recommendations that improve as students engage more with the platform.

The NBS system identifies the most beneficial next steps for students to take to enhance their college applications based on all the activities they have completed up to that point. We have developed an algorithm that generates a directed acyclic graph that identifies the most common paths of activities that successful students take. One of the early insights from this model is that more successful students interact with college pages on the NCSA platform more frequently. Implementing the NBS system will offer students tailored, around-the-clock recommendations to improve their recruitment prospects.