• T. Naga Navya
• Praneetha Chutla
• Dudekula Haseena
• Thanmayee Kopparapu
• Devarakonda Karuna

The graph given in my analysis of prediction with the use of the SVM algorithm of the mental health compared three models: SVM, Naive Bayes, and Logistic Regression. The line on the graph showing most fluctuation explains high sensitivity to input features-a reason why SVM is especially viable in finding subtle symptoms of issues related to mental health: early undiagnosed or even complex cases. In comparison, NB and LR are better predictions for stability, perhaps at the expense of minor changes in symptomatology. SVM is now the best hope for a good predictive model of mental health outcomes from the standpoint of describing complex relationships in the data.

Mental illness prediction, Mental health care, Support Vector Machines (SVM), Psychological test data, Personal Information, Mental health disorders, Depression, Anxiety.

"Predicting Mental Health illness using SVM Algorithm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 11, page no.322-329, November-2024, Available :http://www.jetir.org/papers/JETIRGO06032.pdf

"Predicting Mental Health illness using SVM Algorithm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 11, page no. pp322-329, November-2024, Available at : http://www.jetir.org/papers/JETIRGO06032.pdf