This study applied innovative data mining techniques to a community survey dataset to develop prediction models for two aspects of physical activity (active transport and screen time) in sample of older, primarily Hispanic, urban adults (N=2, 514). Main predictors for active transport (accuracy=69.29%, precision .67, recall .69) were immigrant status, high level of anxiety, having a place for physical activity, and willingness to make time for physical activity. The main predictors for screen time (accuracy=63.13%, precision .60, recall .63) were willingness to make time for exercise, having a place for exercise, age, and availability of family support to look up health information on the Internet. Data mining methods were useful to identify intervention targets and inform design of customized interventions.