Significance of Non-Academic Parameters for Predicting Student Performance Using Ensemble Learning Techniques

The academic institutions are focusing more on improving the performance of students using various data mining techniques. Prediction models designed to predict at a very early stage so that preventive measures can be taken beforehand. Various parameters (academic as well non-academic) considered student different classifiers. Normally, given weightage in predicting student. This paper compares two models: one built only and another both non-academic (demographic) parameters. primary set has been from technical college India, which consists 6,807 containing attributes. Synthetic minority oversampling technique filter is applied deal with skewed set. eight classification algorithms then compared find help give most appropriate model classify based his performance.