Rough Sets Theory Based Approach for Predicting Studentś Performance in e-Learning Systems

In the recent days, educational data mining Strategies have captured the notice of Scientists according to the rapid growth of educational data and the need for developing methods to discover the hidden knowledge to predict the success of students’ learning. Many methods are used in the previous literature such as ANN, SVM, Naive Bayes classifiers and logistic regression. The original motivation of this work is to fill the gap between the very large dynamic data on educational institutions and the computational programming tools which is not sufficient to find solutions in some cases. The current work proposes a strategy based rough sets theory to generating a set of classification rules to predict student’s performance in the e-Learning Systems. The data of 480 student records and 16 features are used to fetch all reducts and finally a set of classification rules are created to build a knowledge base with excellent accuracy to find the relationship between student’s behaviors and their academic. The findings of this study are expected to give the educational institutions the chance for early interference to prevent the potential failure of students to achieve learning objectives by making changes to learning strategies. as well as predict students who have a high chance of achieving academically, solve student academic problems, optimize the educational environment, identify key factors that influence student academic success and explore the relationships between these key factors and enable data-driven decision making.