A Genetic-Fuzzy Based Mathematical Model to Evaluate The Distance Education Students’ Academic Performance

In distance education systems, it is very important to predict academic performance for both instructors and students during the course of the semester. If an instructor can properly assess and predict student performance early at the beginning of the semester, then the instructor can take action and arrange both the course content and the teaching style. This, in turn, contributes greatly to the success of students. In order to make such a prediction, constructing mathematical models is one of the most effective and efficient methods. Among many approaches, fuzzy logic-based models have the most appropriate topology. In this study, fuzzy logic model is used to model data of distance education and predict students’ academic performances. In order to increase the success of fuzzy logic model, fuzzy membership functions are optimized by using genetic algorithms. As distance education data, when students enrolled in learning management system, how frequently they log on, and how long they stay online are used. By using this model and data of a 6 week-long study, students’ success level at the end of the semester is predicted and the results are compared with the ground truth data.