Machine Learning-based Model for Talented Students Identification

Abstract

Identifying the talented university students plays an important role in higher education. Special curriculum can be developed for these students as an outcome from the identification process. This curriculum can be compacted, clustered, and accelerated to match and exploit students’ abilities. Current methods for identifying talented students are based on simple identification test in the form of a questionnaire, which is developed for specific age. However, this method of identification cannot cover all aspects of student abilities and inaccurate as it not an iterative process. In this paper, a machine learning approach is proposed for identifying talented students based on their academic performance, which is evaluated repeatedly through their study. In this approach, we measure a set of features representing student abilities, then cluster them based on their features similarity. The proposed approach is applied on a set of 100 university students and shows promising results in identifying the talented group. To emphasize their talent, this group is guided to participate in national competitions that match their abilities, and they could achieve significant ranks.