Student Consultancy Service: Prediction of Course Grades in Course Selection Phases Using Artificial Intelligence Techniques

Abstract

Universities offer technical elective courses to allow students toimprove themselves in various parts of their majors. Eachsemester, the students make a decision regarding these technicalelectives, and the most common expectations students have inthis context include, getting education at a better school, gettinga better job, and getting higher grades with a view to securingadmission into more advanced degree programs. Electing acourse on the basis of the interests and skills of the student willnaturally translate into achievement. Advisors, in this context,play a major role. Yet, the substantial workload advisors havealready assumed prevent them dedicating enough time forexploring the interests and skills of the students, and hencehinder the development of the required relationship betweenstudents and their advisors. This study attempts to estimate theachievement level a student intends to elect, on the basis ofgraduate data received from the database of students of SakaryaUniversity, Faculty of Computer and Information Sciences, andled to the development of a decision-support system. Theapplication used ANFIS and artificial neural network methodsamong the artificial intelligence techniques, alongside the linearregression model as the mathematical model, whereupon theperformance of the methods were compared over theapplication. In conclusion, it was observed that artificialintelligence techniques provided more relevant resultscompared to mathematical models, and that, among theartificial intelligence techniques feed forward backpropagationneural network model offered a lower standard deviationcompared to ANFIS model.