A Graduate School Recommendation System Using the Multi-Class Support Vector Machine and KNN Approaches
Alisha Baskota, Yiu‐Kai Ng · 2018
With the advancement in technology and increased demand on skilled workers these days, education becomes a stepping stone in securing jobs with long-term perspective. As competition for admission into higher education increases, it becomes even more important for applicants to find graduate schools that fit their requirements and expectation. Selecting appropriate schools to apply, however, is a time-consuming process, especially when looking for schools at graduate level due to the various factors in decision making imposed by the schools and applicants. In this paper, we propose a recommendation system that suggests appealing graduate programs to students based on the Support Vector Machine and K-Nearest Neighbor approaches. As graduate programs make decisions based on applicants' qualification, our recommender considers user's personal data and data of various graduate programs obtained from online education portals to make suggestions. We conduct an empirical study using data of current graduate schools and former graduate school applicants, and the performance evaluation validates the merit of our suggestions.