 This research demonstrated that a machine learning algorithm can accurately identify individuals who are likely to engage in high-intensity binge drinking behavior. The algorithm was able to distinguish between those who were classified as non-bingers and those who were classified as high-intensity bingers. The most important factors for predicting this outcome were alcohol consumption levels, self-reported effects of alcohol, compulsive drinking subscale scores, and presence of a current psychiatric diagnosis. Additionally, smoking behaviors, perceived stress, IQ, and number of negative life events were also found to be significant predictors. These findings suggest that the algorithm may be useful in identifying individuals at risk for high-intensity binge drinking behaviors which could help inform prevention efforts and interventions. This article was authored by James Keone Morris, Josh L. Gowen, Melanie L. Schwant and others.