Development of College Completion Model Based on K-means Clustering Algorithm

Abstract

—The amount of data stored in educational databases is rapidly increasing because of the increase in awareness and application of information technology in the field of higher education. What can be done with these databases is to mine the hidden knowledge in it. This paper is designed to present and justify the capabilities of data mining. The main contribution of this paper is the development of college completion model based on k-means clustering algorithm. The data stored in the Student Information and Accounting System from 2009 to 2013 was used to perform an analysis of study outcome taking into consideration not to include in the final result any identifying information to protect their privacy. The results showed that majority of the students belong to the cluster which needs intervention. The dataset used can be improved by including data of students currently enrolled. The result obtained can be used as a decision support tool. The WEKA software was used to build the college completion model using k-means clustering.