Applying Deep Learning Neural Networks in Predicting Students’ Cumulative Grades
Elmasry1, Mohamed Abbas2
1Elmasry*, National Egyptian E-Leaning University (EELU), Giza, Egypt.
2Mohamed Abbas, National Egyptian E-Leaning University (EELU), Giza, Egypt.
Manuscript received on December 02, 2020. | Revised Manuscript received on December 05, 2020. | Manuscript published on December 30, 2020. | PP: 293-297 | Volume-10 Issue-2, December 2020. | Retrieval Number: 100.1/ijeat.B20841210220 | DOI: 10.35940/ijeat.B2084.1210220
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The distinguished universities aim to provide quality education to their students. One way to achieve the highest quality in university studies is to discover knowledge to predict student performance and grades in courses etc. Recently, the amount of data stored in educational databases is accumulating very quickly, as these databases contain indirect information that can be used to improve student performance. Academic performance is affected by many factors, so it is necessary to predict student performance to determine the difference between students who are excelling in studies and students who need to exert more effort to improve their performance and their level of achievement. Hidden or Indirect knowledge is part of the educational data set and can be extracted using various means, such as data mining techniques and the use of classification, and deep learning through neural networks. This paper has been designed to extract knowledge describing students’ performance in the courses required for graduation, in a way that helps academic advisors in providing academic advice and guidance to students to improve their cumulative grades.
Keywords: Deer Learning, Neural Networks, Classification, Data Mining, Academic Performance, CGPA.
Scope of the Article: Deep Learning