A fuzzy decision support system for monitoring student academic performance and supporting early intervention

In digital learning environments, monitoring of students’ learning behavior is challenging due to the uncertainty, incompleteness, and gradual changes in student learning behavior. Current prediction models may achieve good performance but offer little interpretability and limited support for timely academic intervention. This study proposes an interpretable Fuzzy Decision Support System (FDSS) for monitoring student academic performance and supporting early intervention strategies. It combines academic, behavioral, and engagement measures from the xAPI-Edu-Data dataset with a Mamdani fuzzy inference mechanism, triangular and trapezoidal membership functions, and centroid defuzzification. The FDSS was assessed using classification measures, early-warning analysis, sensitivity testing, and comparison with baseline machine learning models. The proposed system achieved an overall accuracy of 0.86, a macro-averaged F1-score of 0.84, an AUC of 0.91, and a High-Risk recall of 0.89. The results indicate that the FDSS is a viable tool for predicting academic performance and for providing rule-based academic intervention support that is transparent to the user.