Forecasting of University Students' Performance Using A Hybrid Model of Neural Networks and Fuzzy Logic

Abstract

aAplied in forecasting the academic performance of university students, with aim of detecting the factors that influence their learning process which allows instructors and university administration to take more effective actions to increase the university student's performance. Identifying the students' performance will improve the quality of education which will be through analyzing and forecasting the students' performance at the course level and degree level. This research focuses on first-year students' performance in two university-requirement courses, depending on features such as attendance, assessment marks, exams, assignments, and projects. Forecasting the students' performance in the whole degree will depend on these features; high school average, Grade Point Average (GPA) for each semester, drop courses, selected core courses in the degree, period of study, and final GPA. A hybrid Adaptive Neuro-Fuzzy Inference System (ANFIS) model was used to perform the forecasting process. In this way, based on the datasets collected from the selected courses, or the whole degree, the future results can be forecasted and suggestions can be made to carry out corrective steps to improve the final results. The experiments result of the applied models performed that ANFIS-Grid outperforms the ANFIS-Cluster, wherein each model produces the lowest error of 0.7%, where it just fails in one sample from thirteen samples, while the ANFISClus