The experimental results in developing a predictive model using the decision support system algorithm for identifying the mental health condition of university students are presented in this paper. The predictive models aim to specify a probabilistic model that will provide a good fit to data testing that estimates the model’s parameters. The model was trained to utilize a data science software platform that provides an integrated environment for predictive analytics. The model’s mental health prediction accuracy for depression is 59.14%, 56.67% for anxiety, and 63.70% for stress. The results of the model were encouraging; nevertheless, training data must be enhanced in terms of sample selection, and more advanced computational specifications should be explored in order to experiment more and for faster training.