Prediction Analysis Of Student Admission To Information Technology Education (ITE) Programs Using Classification Algorithm

Data mining has a significant impact on the business world to analyze the available data, which helps the organization support decision-making. On the other hand, schools, universities, and colleges adapt educational data mining and artificial intelligence to analyze the available data to improve educational policy. In this study, four classifiers-Decision Tree, K-Nearest Neighbor, Logistic Regression, and Naive Bayes-were used as part of a classification process. This study will be helpful to the university that offers an Information Technology Education (ITE) program for student admission based on the information technology selected predictors in this study. There were 8 predictors selected based on the correlation coefficient evaluation. The strongest predictor was the mathematical skill which gained 0.767. dditionally, the accuracy, precision, recall, and f1 score of each classifier's performance have all been examined. However, K-Nearest Neighbor perceived the highest accuracy with 93.18%, precision gained 97.98%, the recall had 88.13% and the F1 score percentage had 92.76%.