Data Driven System To Predict Academic Grades And Dropout In Higher Education

Abstract

Nowadays, With the digitization of the systems in the universities, academic institutions create a large volume of student-related data using computerized form. For the exploration of hidden information from this golden data, a lot of techniques and tools, introduced in recent years, help the data analysis process become easier than ever before. In higher education systems, applying a data driven system can help them take advantage of this data resource for the research of talent or final year students, and scientists in many departments to analyze behaviors, affecting factors… Instead of wasting the resources for storing useless data, This can be a new approach to have general and multi-dimensional insights to improve the education qualification day by day. The changes are based on the actual data of the university itself. Along with the data driven system, Data mining, which is used as an analytical tool, becomes essential for these departments to transfer substantial amounts of data and manipulate it into useful knowledge. Therefore, educational data mining techniques were created for constructing predicting or classifier models built from the student historical records. In this context, automated systems supporting the lecturer are needed. One significant problem is not being able to predict a student's academic grade in a course, which would help them to achieve better results in the future course. Therefore, the main goals of this research are to explore and implement the efficiency of machine learning in the field of Educational data mining, especially in predicting aspects of student’s performance, including Grade prediction, Dropout or Course recommendation system in advance…