Data mining for predicting students' learning result

Data mining in educational field has been commonly used to analyzed pattern in academic databases that hard to analyze manually. The main objective of this paper is to compare the performance of data mining algorithms to predicting students' learning result based on student academic data set from inside the academic databases nor outside the academic databases using two data mining algorithms (Naïve Bayes Classifier and Tree C4.5) based on the accuracy and precision percentage for both algorithms. The result for data set that has been given to build the models shows that Naïve Bayes Classifier and Tree C4.5 averages accuracy is above 60% just like the precision averages of Naïve Bayes Classifier, the precision averages of Tree C4.5 only gain 58.82% but have a lower average of precision distinction. This study can be extended by using other data mining algorithm like association rule or expanded data set to increase the algorithm performance.