Predicting and Analysing University Dropout Rates using Machine Learning Methods

Data analysis provides constructive outcome to the student performance, allowing teachers and administrators to categorize areas of strength and areas for improvement. This helps them to develop targeted strategies for teaching, learning and growth. To ascertain the most effective technique for evaluating the learning environment and the elements that affect students' academic achievement, the prior studies have been reviewed. The data mining approaches presented in this work may be used to forecast student graduate performance, dropout, and discover relevant elements that may impact students' performance using regression models. Several of the strategies have demonstrated excellent accuracy in their results. Aside from this study, it may be known which methods are more suited and yield the most accuracy when assessing students' performance.