Using K-Means to Determine Learner Typologies for Project-based Learning: A Case Study of the University of Education, Winneba

Currently, academic instructors in Ghana have some difficulty in grouping students for projects-based courses because of increasing student numbers. One of the recent challenges educational institutions and instructors are facing is the explosive growth of educational data and how to use this data to improve the quality of teaching. K-means clustering is an unsupervised Data Mining technique for grouping large datasets with insightful similarity patterns to expose hidden trends and behavior in each cluster. The purpose of this research is to apply K-means clustering algorithm to analyze students’ clusters for centered project-based learning. This research uses K clusters of 20. The clustering gave a low within cluster Sum of Square Error (SSE) of 3.60889. Clusters 1 and 6 have the highest member set of 32 each whiles clusters 8 and 9 have the lowest member set of 2. The results show that the K-means clustering algorithm is effective in grouping learners based on similar characteristics that indicate their performance. Assessments can also be tailored to suit all categories of learners for efficient results in project-based courses.