Predicting student performance is very important to the success of any educational process. Harnessing methods of data mining and machine learning to predict their performance based on data available in schools and student records can explain their behavior, the impact of each factor on the progress of the educational process for students, the relationship of the age stage and follow-up of parents and days of absence. This paper discusses the possibility of harnessing machine learning algorithms to predict student performance and determine the importance of each factor to that performance and Comparing the performance of machine learning algorithms (GBDT-RFDT-Deeplearning) in exploring educational data.
