<![CDATA[Improving students' academic performance is a key goal in the context of higher education. However, the process of identifying students who require additional support is often complicated and complex. Traditional approaches in analyzing student performance data tend to be limited in handling data uncertainty and complexity. Therefore, the development of fuzzy logic-based decision-making systems is becoming increasingly important. This research aims to develop a fuzzy logic-based decision-making system to predict student performance accurately and efficiently. This approach utilizes fuzzy logic concepts to handle uncertainty and complexity in data, and allows the integration of various input factors, such as exam results, class participation, and other variables, in the decision-making process. The research methods include collecting historical student performance data, modeling fuzzy variables for inputs and outputs, developing fuzzy inference rules, and implementing and testing the system using split test data. Numerical example results show that the system is able to provide predictions of student performance by considering relevant input variables. In addition, the system also offers the potential to improve the efficiency of educational interventions by identifying at-risk students faster and more precisely. As such, the development of this fuzzy logic-based decision-making system is expected to make a significant contribution to efforts to improve the quality and equity of higher education by ensuring that every student gets the support they need to reach their full academic potential.]]>
Copyrights © 2024
