Suicide is one of the most important health and social issues in different societies that has a devastating impact on the individual, family, and society. Every year, a large number of people commit suicide for various reasons, which has become a serious problem in many countries. This phenomenon, especially among soldiers and military forces, takes on special dimensions. Due to their stressful nature, military environments can increase suicidal thoughts in soldiers. Various organizations and systems are looking for solutions to reduce and prevent suicide. One of these solutions is the use of new technologies such as intelligent systems and artificial intelligence algorithms. The present study aimed to build a machine learning model to prevent suicide in military personnel. This study first identified the dimensions and components affecting suicide using a qualitative method and documentary studies, and based on these dimensions, a dataset including information on soldiers who had previously attempted suicide was collected and quantitatively analyzed. In the next step, three supervised learning algorithms (neural network, random forest, and support vector machine) were used to train the prediction model. Data normalization was also performed to improve the accuracy of the models. Finally, an application was designed that automatically calculates an individual's suicide risk and predicts the percentage of its probability of occurrence by receiving personal and family, psychological, and personality information. The results of the research show that the use of artificial intelligence algorithms can serve as an effective preventive tool in identifying individuals at risk of suicide.