Prediction Model on Student Performance based on Internal Assessment using Deep Learning

Sadiq Hussain, Zahraa Fadhil Muhsion, Yass Khudheir Salal, Paraskevi Theodorou, Fikriye Kurtoğlu, G. C. Hazarika


Educational Data Mining plays a crucial role in identifying academically weak students of an institute and helps to develop different recommendation system for them. Students from three colleges of Assam, India were considered in our research which their records were run on deep learning using sequential neural model and adam optimization method. The paper compared other classification methods such as Artificial Immune Recognition System v2.0 and Adaboost, to find out the prediction of the results of the students. The highest classification rate was 95.34% produced by the deep learning techniques. The Precision, Recall, F-Score, Accuracy, and Kappa Statistics Performance were calculated as a statistics decisions to find the best classification methods. The dataset used in this paper was 10140 student records. Directing the student for their future plan comes from discovering the hidden patterns by using Data Mining techniques.


Educational Data Mining; Deep Learning; Classification; academically weak students

Full Text:


Copyright (c) 2019 Sadiq Hussain

International Journal of Emerging Technologies in Learning (iJET) – eISSN: 1863-0383
Creative Commons License
Scopus logo Clarivate Analyatics ESCI logo EI Compendex logo IET Inspec logo DOAJ logo DBLP logo Learntechlib logo EBSCO logo Ulrich's logo Google Scholar logo MAS logo