Title: Predicting and preventing student failure – using the k-nearest neighbour method to predict student performance in an online course environment

Authors: Tuomas Tanner, Hannu Toivonen

Addresses: Typing Master Finland Oy, Eerikinkatu 4 A 16, FI-00100 Helsinki, Finland. ' Department of Computer Science and HIIT, University of Helsinki, P.O. Box 68, FI-00014, Finland

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.

Keywords: k-nearest neighbour; KNN; algorithms; student prediction; e-learning; online learning; performance assessment; electronic learning; predictive methods; teacher aids; machine learning; data mining; failure prevention; student failure; student performance; online courses; internet; world wide web; touch-typing; tests; skills testing; predictors; final scores; skill-based courses; early warnings; Finland; learning technology.

DOI: 10.1504/IJLT.2010.038772

International Journal of Learning Technology, 2010 Vol.5 No.4, pp.356 - 377

Published online: 02 Mar 2011 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article