The primary goal of any educational institution is to provide students with the best possible education and skills. To achieve this objective, it is necessary to identify students who require additional assistance and take effective steps to improve their academic performance. To produce optimal outcomes and reduce the risk of failure, educational programs need innovative methods of enhancing school efficiency. The Educational Decision Support System (EDSS) has recently gained popularity in the education system, as it enables continuous monitoring and assessment of student outcomes. However, inadequate information systems face difficulties and obstacles in utilizing EDSS to its full potential due to imprecise data, insufficient characterization, and inadequate databases. Therefore, a comprehensive literature review and selection of the most accurate predictive methodology are critical to improve the prediction process. In this study, machine learning methods were employed to construct a classifier that can predict students' success in the economic field. This paper proposes a knowledge base DSS model that utilizes machine learning techniques to evaluate student performance based on their mid-term and final-term exam results.

DSS, Artificial Neural Network, SVM, ML, Regression