부산대학교 도서관

Predicting learners' prospective performance depending on their current educational data is critical for implementing appropriate educational measures for guaranteeing learners' timely and acceptable graduation. Though there is a large body of research on predicting students’ performance when resolving issues or preparing for classes employing statistical methods, predicting students’ performance when finishing degrees is a new area of research. Techniques enable machines to arrive at judgements for humans in artificial intelligence (AI). This technology improves the consumer encounter in a variety of manners. Numerous research in the realm of education were undertaken to address the issue of learner focus and performance employing different Machine Learning (ML) methods. We demonstrate that the suggested technique outperforms standard methods in extended simulations on an undergraduate learner database gathered over a 3-year period at UCLA.