In this study, we identified factors influencing completion rates (graduation) of undergraduate students in science, technology, engineering, and mathematics (STEM). We used hierarchical, logistic, and linear regression models to analyze the data and found significant predictor variable interactions across various underrepresented versus well-represented student groups. We asked six research questions, three involving two- and three-way interactions between STEM completion, underrepresented groups, and predictor variables and three involving two- and three-way interactions among time spent for graduation, predictor variables, and underrepresented groups. We found that female STEM students completed their degree in significantly less time than their male counterparts (p < .001) and that for every 1 point increase in second-year grade point average, length of time to complete the bachelor’s degree decreased by 1.68 years. These and other findings can be used by institutions to help focus retention intervention efforts on those critical and significant predictors of STEM degree completion of underrepresented groups.