<![CDATA[Student academic performance assessment is not only determined by exam scores, assignments, and attendance but also influenced by other factors such as attitude. However, evaluating this factor tends to be subjective. Additionally, the absence of an early prediction system to estimate students' academic performance can hinder timely study finish for at-risk students. The purpose of this study is to use the Mamdani fuzzy logic method to develop a system for predicting student academic performance. The input variables used in this system include attendance, assignments, midterm exams, final exams, and attitude. The system is modeled using fuzzy membership functions and assessed based on appropriate weightings. The inference process is conducted based on a set of fuzzy rules and is determined by the combination of input values. The next stage is defuzzification, which is the process of generating a final value used to classify academic performance into categories of "poor," "fair," or "good." This system is developed using the Python programming language with the scikit-fuzzy library and tested using the Mean Absolute Percentage Error (MAPE) method. The test results show an error rate of 1.35%. These results indicate that the Mamdani fuzzy logic approach is considered effective in assisting the assessment of student academic performance.]]>
Copyrights © 2025
