Constructing a Predictive Model for High School Students' Enrolment Results

Abstract

Nowadays, data-informed decision-making can assist high-school educational decision-making, especially student test scores, and further education data, then these data can be used to inform decision-making in schools and boost overall school performance. We aimed to assess the relationships among high school students' admission scores, academic performance at school, and psychological tests in the school system. The relationships were used to predict the departmental fields and universities that students would select for advanced studies in the future. This research will utilize data mining algorithms, including Naïve Bayes, SVM, and Neural Network classifiers, to extract and analyze hidden patterns in students' academic records and credentials. When the Bayesian Network model was used to predict whether a student's university is public or private, our results showed 78.46% of the predicted results. Predicting the accuracy of the top three departmental fields, the SVM model achieved the highest performance with an accuracy of 69.77% .Given that students' academic performance varies across high schools, each school should develop its customized predictive model using only its students’ data. This will help students believe in and pursue their interests.