Please use this link to access this publication. Abstract Background Cannabis use is common, particularly during emerging adulthood when brain development is ongoing, and its use is associated with harmful outcomes for a subset of people. An improved understanding of the neural mechanisms underlying risk for problem-level use is critical to facilitate the development of more effective prevention and treatment approaches. Methods In the current study, we applied a whole-brain, data-driven, machine learning approach to identify neural features predictive of problem-level cannabis use in a nonclinical sample of college students (n = 191, 58% female) based on reward task functional connectivity data. We further examined...