Application of optimum binning technique in data mining approaches to predict students’ final grade in a course

Abstract

In Bangladesh there is a continuous rise in demand for higher education in last decade; therefore, the need for improving the education system is imminent. Data-mining techniques could be explored on educational settings to extract useful information which could be helpful for the students as well for the instructors. In this research, we present and analyze techniques that predict students’ final outcome (with respect to grade) for a particular course. We validate our method by conducting experiments on data that are related to grade for courses in North South University, one of the leading universities in higher education in Bangladesh. Our preliminary finding is encouraging. We further improve and extend our ideas through discretization of the continuous attributes by equal width binning and error minimization techniques. Experimental results demonstrate that improved technique through discretization outperforms the techniques with other forms such as probability estimation by almost 7-10%.