Most of e-commerce sites use recommendation systems as the underling tools for providing recommendation to users to help them find what they really want. Collaborative recommendation systems recommend items to target user based on similarity between past behaviors of target user and other users. In this paper, we propose a collaborative recommendation approach that recommends university elective courses to students by exploiting what other similar students have taken. Our system employs an association rules mining algorithm as an underlying technique to discover patterns between courses. Experiments were conducted with real datasets to assess the overall performance of the proposed approach.