Forecasting the risk for mental disorders from early ecological information holds benefits for the individual and society. Computational models used in psychological research, however, are barriers to making such predictions at the individual level. Preexposure identification of future soldiers at risk for posttraumatic stress disorder (PTSD) and other individuals, such as humanitarian aid workers and journalists intending to be potentially exposed to traumatic events, is important for guiding decisions about exposure. The purpose of the present study was to evaluate a machine learning approach to identify individuals at risk for PTSD using readily collected ecological risk factors, which makes scanning a large population possible. An exhaustive literature review was conducted to identify multiple ecological risk factors for PTSD. A questionnaire assessing these factors was designed and distributed among residents of southern Israel who have been exposed to terror attacks; data were collected from 1,290 residents. A neural network classification algorithm was used to predict the likelihood of a PTSD diagnosis. Assessed by cross-validation, the prediction of PTSD diagnostic status yielded a mean area under receiver operating characteristics curve of .91 (<em>F </em>score = .83). This study is a novel attempt to implement a neural network classification algorithm using ecological risk factors to predict potential risk for PTSD. Preexposure identification of future soldiers and other individuals at risk for PTSD from a large population of candidates is feasible using machine learning methods and readily collected ecological factors.