Effective models for predicting Gaokao scores and selecting universities for college admissions in mainland China

Abstract

Students in mainland China would need to predict the admission Gaokao score for a major of a university to increase their chances of acceptance to a best-suited major and a university. Early prediction methods are empirical without the backing of in-depth data studies. We fill this void by presenting well-tested mathematical models, based on the ranking of Gaokao scores in a provincial administrative region. In addition, we devise a recommendation model that uses general morphological analysis to help students explore universities and majors that match their abilities and interests, and a baseline recommendation index for scoring each choice. We use the technique for order preference by similarity to find the best university tailored to every applicant. We show that our prediction methods significantly outperform the methods commonly used by teachers and experts and can predict admission scores with an accuracy of up to 94.7%. We then present case studies to demonstrate the effectiveness of our recommendation model.