Early Prediction on Students Performance

In this is the Early indications regarding students’ progress help academics to the optimize there are learning strategies and focus on to the diverse educational practices to make at the learning experience successfully. It is the Machine learning application can help to the academics predict their expected weaknesses in the learning processes and as the result they can proactively engage such as students in better learning experience. We applied the logistic regression, linear discriminant analysis, K-nearest neighbors, classification and regression trees, gaussian Naive Bayes and support vector machines on historical data of student grades one of the undergraduate courses and developed the model to predict there are this grade of students taking the same course in the next term. the experiments show Linear discrimination analysis as the most effective approach to the correctly predict to the students’ performance outcome in final exams. Then these students total 54 records, 49 predicted by model as the expected giving 90.74.