Stress Prediction of Students using Machine Learning

On the daily basis, people are suffering from the stress illness because of many factors which include the social factor, external stimulus or environment factors and internal factors. In healthcare, vast development have been made with the use of machine learning. Stress is a fatal disease causing a considerable number of fatalities across the world. The machine learning enable the prediction of the possibility of stress prediction in the under studies of students like, graduate, under graduate, post graduate and professional students. In this paper we analyze the performance of machine learning techniques to reduce the risk of stress prediction resulting in early treatment of the understudies' students. The data set was collect from university with the help of pss scale and it made up of more than 200 student's data. Different types of classification algorithms Naive Baye's, Linear Regression, Multi- layer perceptron, Bayes Net, J48 and random forest are using and also we calculate their accuracy with the help of performance parameter like TP, FP, ROC, FMeasure etc . In this research Random forest classifier gives high accuracy of 94.73%