Predicting student’s GPA via educational data mining / Dr Wan Fairos Wan Yaacob … [et al.]

Data mining technique is widely used to analyze large amount of data in many areas including educational field. Educational Data Mining (EDM) has been emerged due to growing availability of educational data and the need to analyze huge amount of data that generated from the educational ecosystem. EDM is a multidisciplinary field that covers the area of analyzing educational data using data mining. These techniques are recentlybeing used in various applications. The four areas of applications that have received particular attentions, including individual learning from educational software, collaborative learning, computer-adaptive testing and analyzing students’ performance. One of the applications is the ability to predict the student performance. Recently, Educational Data Mining helps the educational institution to adapt with a new teaching technique for the learning processes and learners. Educational institutions can gain deep and thorough knowledge to enhance its lesson plan, assessment, evaluation planning and decision-making based on EDM. EDM offers many techniques such as Decision Trees, Naïve Bayes, Neural Networks, K-Nearest neighbor, Logistic Regression and many others. Many kinds of knowledge can be discovered using these techniques such as association rules, classifications and clustering.
Nowadays, universities are operating in a very complex and highly competitive environment. The main challenge for modern universities is to deeply analyze their performance, to identify their uniqueness and to build a strategy for further development and future actions. Thus, the aim of this research paper is to develop predictor model in predicting students’ GPA via educational data mining which helps to determine the most important and influencing course of final GPA for each semester. In this research the decision tree was used to evaluate students’ performance for data classification.