Publication: A Machine Learning Classification Application to Identify Inefficient Novice Programmers
Date
2021
Authors
Khan I.
Al-Mamari A.
Al-Abdulsalam B.
Al-Abdulsalam F.
Al-Khansuri M.
Iqbal Malik S.
Ahmad A.R.
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Science and Business Media Deutschland GmbH
Abstract
To preserve their reputation and prestige, the educational institutes are required to provide evidences of their students� academic performance to the governmental bureaus and accreditation agencies. As a consequence, the monitoring individual student academic performance is emerging as a vital task for the educational institutes. The indispensability of this prediction amplifies when it comes to programming language course; which emerges as backbone for Computer Science students. Machine Learning classifiers are considered as productive tools to develop models which can identify the students with inefficient academic performance. The early identification of inefficient students will provide an opportunity to instructor to take appropriate precautionary measures. This paper proposes a prediction model with an added application layer with graphical user interface. The experimental part of paper compares the performance of several machine learning algorithms and comes up with k-NN as appropriate classifier in the addressed context. Further, the application layer of the proposed architecture facilitates instructor with a Graphical User Interface to execute a wide range of operations. � 2021, Springer Nature Switzerland AG.
Description
Data mining; Graphical user interfaces; Learning algorithms; Machine learning; Nearest neighbor search; Academic performance; Application layers; Computer science students; Educational data mining; Educational Institutes; K-near neighbor; Machine learning classification; Nearest-neighbour; Novice programmer; Productive tools; Students