PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Predicting and preventing student failure - using the k-nearest neighbour method to predict student performance in an online course environment
Tuomas Tanner and Hannu Toivonen
International Journal of Learning Technology Volume 5, Number 4, pp. 356-377, 2010. ISSN 1477-8386

Abstract

We study the problem of predicting student performance in an online course. Our specific goal is to identify at an early stage of the course those students who have a high risk of failing. We employ the k-nearest neighbour method (KNN) and its many variants on this problem. We present extensive experimental results from a 12-lesson course on touch-typing, with a database of close to 15,000 students. The results indicate that KNN can predict student performance accurately, and already after the very first lessons. We conclude that early tests on skills can also be strong predictors for final scores also in other skill-based courses. Selected methods described in this paper will be implemented as an early warning feature for teachers of the touch-typing course, so they can quickly focus their attention to the students who need help the most.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:User Modelling for Computer Human Interaction
ID Code:7893
Deposited By:Hannu Toivonen
Deposited On:17 March 2011