Classification of student success using Random Forest and Neural Networks

In recent years online education has overgrown be-cause of the many advantages it offers. During courses, different institutions collect and analyze student performance data to improve their educational experience. One of the main challenges of online education is being able to detect those students who have difficulties completing the course. This paper presents an approach to classify student success based on Random Forests and Neural Networks. One of the characteristics of Random Forests is that the algorithm selects the best feature to split the data. The selection of the most relevant features were used to train the Neural Network models.