Accurately forecasting course enrollment rates in higher education is of great concern in order to minimize unnecessary administrative costs as well as burden to both students and faculty. At San Diego State University, courses with high enrollment variation from year to year are often inaccurately forecasted using current methods.This study aims to first recreate existing course enrollment prediction models using student data from San Diego State University and then to improve upon those methods by introducing a decision tree model based on the CART algorithm as well as a second model based on the random forest algorithm. This study also aims to introduce demographic and prior academic information in to the aforementioned algorithms to ascertain their influence on improving course enrollment prediction accuracy. The study will use these strategies to predict enrollment in CHEM 200, a general education course at SDSU with historically high and varied enrollment numbers. We will then determine which factors are the most influential in determining whether or not a student will enroll in CHEM 200 using the variable importance metric derived from both tree based algorithms.