Prediction of Students Programming Performance Using Naive Bayesian and Decision Tree

Machine learning strategies are faster than ever in the field of education. Machine learning aims to discover hidden information and students' performance in programming. From this paper, we suggest a model for predicting the performance of students in programming using two classification algorithms: Naive Bayes and decision tree. Information was collected from Bachelor of Computer Application students at affiliated colleges at the University of Madras. The main purpose of such classification strategies may be to help students identify their weak points and improve their programming skills. Teachers can also take corrective measures to improve the students learning in programming Test results show that Naive Bayes is better than the decision tree with a high accuracy of 91.02%.