Data Mining for Intelligent Academic Advising from Noisy Dataset

This paper proposes an approach to address the common problem of classification from educational dataset with irrelevant or redundant attributes. In particular, the paper focuses on using this approach to improve academic advising through intelligent prediction of students’ performance. This is achieved by using a composition of the two popular classification methods: Decision Trees and Naïve Bayesian Classifiers. Naïve Bayesian Classifier is built using the significant attributes in the students’ dataset that are identified by the Decision Tree. The results show that the proposed approach succeeded in identifying the main attributes affecting students’ performance. Moreover, the evaluation results show that using a composition of Naïve Bayesian and Decision Trees in one approach outperformed the results of each classifier individually.