Objective: 10-50% of college students meet the diagnostic criteria for one or more mental illnesses; unfortunately, less than half seek treatment. This study assessed the predictive power of specific variables on students' use of on-campus mental health resources using the American College Health Association's National College Health Assessment (ACHA-NCHA) II. Participants: Respondents included undergraduate and graduate students ages 18-35 years (n = 96,121). Methods: We analyzed data from the ACHA-NCHA II Fall 2014 and Spring 2015. Andersen's Behavioral Model of Health Services Use enabled selection of predisposing, enabling, and need predictor variables; these were analyzed individually and collectively. Results: Predisposing, enabling, and need variables accounted for 9%, 2.3%, and 17% of the overall variance. Significant variables associated with a student's decision to access on-campus mental health services accounted for 23% of variance total. Conclusions: This insight could allow universities to better recognize students at-risk for needing but not accessing mental health services.