Transfer Learning for Predictive Models in Massive Open Online Courses
Data recorded while learners are interacting with Massive Open Online Courses (MOOC) platforms provide a unique opportunity to build predictive models that can help anticipate future behaviors and develop interventions. But since most of the useful predictive problems are defined for a real-time framework, using knowledge drawn from the past courses becomes crucial. To address this challenge, we designed a set of processes that take advantage of knowledge from both previous courses and previous weeks of the same course to make real time predictions on learners behavior. In particular, we evaluate multiple transfer learning methods. In this article, we present our results for the stopout prediction problem (predicting which learners are likely to stop engaging in the course). We believe this paper is a first step towards addressing the need of transferring knowledge across courses.
Unable to display preview. Download preview PDF.
- 1.Balakrishnan, G., Coetzee, D.: Predicting student retention in massive open online courses using hidden markov models. In: Technical report No. UCB/EECS-2013-109. EECS, University of California, Berkeley (2013)Google Scholar
- 2.Caruana, R.: Multitask Learning. Springer (1998)Google Scholar
- 4.Halawa, S., Greene, D., Mitchell, J.: Dropout prediction in moocs using learner activity features. In: Proceedings of the European MOOC Summit, EMOOCs (2014)Google Scholar
- 5.Huang, J., Gretton, A., Borgwardt, K.M., Schölkopf, B., Smola, A.J.: Correcting sample selection bias by unlabeled data. In: Advances in neural information processing systems, pp. 601–608 (2006)Google Scholar
- 6.Lauría, E.J.M., Baron, J.D., Devireddy, M., Sundararaju, V., Jayaprakash, S.M.: Mining academic data to improve college student retention: an open source perspective. In: Proceedings of the 2nd International Conference on Learning Analytics and Knowledge, pp. 139–142. ACM (2012)Google Scholar
- 9.Street, H.D.: Factors influencing a learners’ decision to drop-out or persist in higher education distance learning. Online Journal of Distance Learning Administration 13(4) (2010)Google Scholar
- 10.Taylor, C., Veeramachaneni, K., O’Reilly, U.-M.: Likely to stop? predicting stopout in massive open online courses (2014). arXiv preprint arXiv:1408.3382
- 11.Tyler-Smith, K.: Early attrition among first time elearners: A review of factors that contribute to drop-out, withdrawal and non-completion rates of adult learners undertaking elearning programmes. Journal of Online learning and Teaching 2(2), 73–85 (2006)Google Scholar
- 12.Veeramachaneni, K., O’Reilly, U.-M., Taylor, C.: Towards feature engineering at scale for data from massive open online courses (2014). arXiv preprint arXiv:1407.5238
- 13.Yang, Q., Pan, S.J.: Transfer learning and applications. In: Intelligent Information Processing, p. 2 (2012)Google Scholar