Prediction Model on Student Performance based on Internal Assessment using Deep Learning
Sadiq Hussain, Dibrugarh University ; Zahraa Muhsion, Yass Salal, Paraskevi Theodoru, Fikriye Kurtoğlu, G. Hazarika
iJET Volume 14, Number 8, ISSN 1863-0383 Publisher: International Association of Online Engineering, Kassel, Germany
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.
Hussain, S., Muhsion, Z., Salal, Y., Theodoru, P., Kurtoğlu, F. & Hazarika, G. (2019). Prediction Model on Student Performance based on Internal Assessment using Deep Learning. International Journal of Emerging Technologies in Learning (iJET), 14(8), 4-22. Kassel, Germany: International Association of Online Engineering.