Predicting student success in a data science degree program is a challenging task due to the interdisciplinary nature of the field, the diverse backgrounds of the students, and an incomplete understanding of the precise skills that are most critical to success. In this study, the applicant's future academic performance in a Master of Data Science program is assessed using information from the admission application, such as standardized test scores, undergraduate grade point average, declared major, and school ranking. Simple data analysis methods and visualization techniques are used to gain a better understanding of how these variables impact student performance, and several classification algorithms are used to induce models to distinguish between students that will perform very well and those that will perform very poorly. Historical admissions and grading data are used to perform these analyses and build the classification models. The analyses and predictive models that are generated provide insight into the factors that identify good and poor candidates, and can aid in future admissions decisions. [For the full proceedings, see ED607784.]