Optimization of Naive Bayes and Decision Tree Algorithms through the Application of Bagging and Adaboost Techniques for Predicting Student Study Success

Abstract

In the Education Assessment Center of the Ministry of Education and Culture, the average grade for each student's subject in the last few years has been below 70. This condition cannot be allowed to continue. A special analysis is needed regarding factors that can help improve student grades. Predictions of student study success are urgently needed. These predictions can anticipate negative impacts that occur, including increased risk of dropout, decreased student motivation to learn, and individual potential that does not develop. The Naive Bayes and Decision Tree algorithms have been used to predict student study success. However, among its advantages, these two algorithms still have several short comings. It can cause the algorithm's performance not to be as expected. Several methods in ensemble techniques can improve algorithm performance. Two methods that are often used and can help improve the performance of classification algorithms are Bagging and Adaboost. This Study will combine Bagging and Adaboost into the Decision Tree and Naïve Bayes algorithms to optimize the results in predicting student success. The stages carried out are initial Study, data collection, data pre-processing,data processing and evaluation model, and analysis of the results. The results show that Bagging and Adaboost techniques have been proven effective in improving accuracy, precision, recall, and F1-Score performance. Combining the naïve Bayes algorithm with Adaboost increases accuracy, precision and recall significantly by 1.95%, 28.98%, and 15.79%.