Providing students with the individualized support that they need, as they need it, has long been a challenge in higher education. Recent improvements in artificial intelligence models have granted an enhanced understanding of student progression and performance. However, this additional knowledge has primarily led to better identification of students at-risk, with minimal information as to why a said student is at-risk or how to best proceed in helping them be successful. This presentation examines the integration of machine learning models to the student support process, utilizing the models to identify the highest priority needs of a student and identify the best intervention method to help support students more effectively.