Abstract
Depression is a psychological disorder that has influenced various factors, including stress, life-style, physical activity, and physical health. It comes with symptoms such as persistent depression, frustration, and attempts to commit suicide. In health care, it is necessary to accurately predict various life situations. Therefore, the concern for this psychological condition, you should recognize the status of an individual, and guide them. Mental health disorders, as a rule, are accompanied by depression. However, it is not the case that there is a great deal of research, and to predict the situations in order to stop the great depression. Therefore, to find the most accurate model to predict depression, we have been working with a number of models for predicting the risk of major depression. In the field of mental health care and treatment, we use the model to determine the condition of the patient, with the aid of a machine learning algorithm. In this paper, we have analyzed the different machine learning algorithms which can predict depression such as Decision Tree, Extra Trees (Ensemble Technique), Random Forest, Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbour (K-3), Naives Bayes are analyzed to find more accurate model to predict depression. This paper also states that the decision tree has a higher accuracy of 85.75%. The proposed model will take the form of information in order to predict the situations and circumstances that may affect the depression, taking into account the contextual information.