Key points are not available for this paper at this time.
The exponential growth of data in the field of education has created a pressing demand for a robust system capable of analyzing this vast amount of information, empowering decision-makers to enhance academic efficiency. By accurately identifying student eligibility for specific courses at the outset, a multitude of challenges, such as dropouts and poor performance, can be effectively mitigated or even prevented. This paper presents a Decision Support System (DSS) that leverages a hybrid data mining model to analyze educational data and unveil concealed patterns and rules. The DSS aims to support decision-makers in enhancing the operational effectiveness of academic institutions by enabling accurate determination of student eligibility for specific courses. To ensure robust analysis, diverse supervised algorithms were implemented, comparative evaluations were conducted, and association rule and unsupervised algorithms were employed to extract hidden patterns. In a case study involving graduates pursuing Master's degrees in Iran, the hybrid model effectively identifies Bachelor's degree majors that exhibit higher likelihoods of success in the targeted course and uncovers additional factors that significantly impact academic performance. The research outcomes highlight the considerable potential of the hybrid model in facilitating informed scholarship decisions and fostering overall institutional efficiency. Furthermore, the proposed DSS could be deployed with various educational datasets, potentially empowering decision-makers with valuable insights to distinguish between successful and unsuccessful students early in the course. This could contribute to optimizing educational outcomes and informing evidence-based policy-making.
Maniyan et al. (Thu,) studied this question.