ABSTRACT
The prediction of academic performance has been a subject of significant interest in the field of education. This study presents a novel approach to predicting students' academic performance using fuzzy logic. The research aims to design and implement a fuzzy inference system (FIS) comprising the fuzzification module, knowledge base, inference engine, and defuzzification module. Historical data and student records were used to train the FIS, creating a robust prediction model based on input variables such as mode of entry, UTME score, secondary school result, and age at entry.
The study also establishes a benchmark for evaluating student performance through the predicted cumulative grade point average (CGPA). This benchmark enables comparisons and assessments of individual students against predetermined criteria. By leveraging fuzzy logic, the model accommodates the inherent uncertainties and imprecisions in educational data, providing a more accurate and adaptable tool for academic performance prediction.
The research contributes to the growing body of knowledge in the field of education technology and data analytics, offering educators and institutions valuable insights into identifying students at risk of underperforming. The findings suggest that fuzzy logic-based approaches hold promise for enhancing educational decision-making and student support systems.
