Clustering approach to examination scheduling

Abstract

The difficulty in examination scheduling is to draw an examination timetable by taking a number of different constraints into account. This paper attempts to optimize two major constraints-to minimize the examination time conflicts and the number of consecutive examinations for a student in a day. Clustering method is applied by analyzing exam enrollments and then groups students into clusters so that students within a cluster are having more similar subject combination to each others than those in another clusters. The purpose of clustering is to effectively arrange the order of exams to be allocated into a suitable exam period. Since exams are scheduled by clusters, it solves the exam conflicts for the students within the same cluster whose are closely related to each other.