Prediction of Retained ICT Skills After Face-to-Face ICT Training Course

Abstract

The Open University of Japan (OUJ) offeres an ICT skills training course for PC beginners since 2010. In this course, students’ ICT skills are measured using a five-point Likert scale at three time points: the beginning of the course (pre-course), the end of the course (post-course), and 0.5–3 years after attending the course (retention). In this paper, we report on the results of analysis of them. We first carried out clustering of retained ICT skills after attending the course using the k-means method. Then, the clusters of retained ICT skills are predicted from the pre-course and post-course skills using the support vector machine. The prediction accuracy of upper / lower clusters was about 80%, which will be the basis for the supports after attending the course.