Prediction of Student's Academic Performance Based on Adaptive Neuro-Fuzzy Inference

Prediction of student’s performance is potentially important for educational institutions to assist the students in improving their academic performance, and deliver high quality education. Developing an accurate student’s performance prediction model is challenging task. This paper employs the Adaptive NeuroFuzzy Inference system (ANFIS) for student academic performance prediction to help students improve their academic achievements. The proposed approach consists of two steps. First, results of the students in the previous exams are preprocessed by normalizing their results in order of improving the accuracy and efficiency of the prediction. Second, The ANFIS is applied to predict the students' expected performance in the next semester. Three ANFIS models viz. ANFIS-GaussMF, ANFIS-TriMF and ANFIS-GbellMF that utilized various membership functions to generate accurate fuzzy rules for the prediction process of the student’s performance are used in this research work. The experimental results showed that ANFIS-GbellMF model surpassed the other ANFIS models with a Root Mean Square Error (RMSE) as low as 0.193.