Intelligent Educational Data Analysis with Gaussian Processes
As machine learning evolves, it is significant to apply machine learning techniques to the intelligent analysis on educational data and the establishment of more intelligent academic early warning system. In this paper, we use Gaussian process (GP)-based models to discover valuable inherent information in the educational data and make intelligent predictions. Specifically, the mixtures of GP regression model is adopted to select personalized key courses and the GP regression model is applied to predict the course scores. We conduct experiments on real-world data which are collected from two grades in a certain university. The experimental results show that our approaches can make reasonable analysis on educational data and provide prediction information about the unknown scores, thus helping to make more precise academic early warning.
KeywordsAcademic early warning Key course selection Course score prediction Gaussian process regression Mixtures of Gaussian processes
The first two authors Jiachun Wang and Jing Zhao are joint first authors. The corresponding author is Jing Zhao. This work is sponsored by Shanghai Sailing Program, NSFC Project 61673179 and Shanghai Knowledge Service Platform Project (No. ZF1213).
- 1.Sun, S.: Computational education science and ten research directions. Commun. Chin. Assoc. Artif. Intell. 9(5), 15–16 (2015)Google Scholar
- 4.Limprasert, W., Kosolsombat, S.: A case study of data analysis for educational management. In: International Joint Conference on Computer Science and Software Engineering, pp. 1–5. IEEE, New York (2016)Google Scholar
- 8.Titsias, M.K.: Variational learning of inducing variables in sparse Gaussian processes. In: Proceedings of the 12th International Conference on Artificial Intelligence and Statistics, pp. 567–574. JMLR, Cambridge (2009)Google Scholar
- 9.Zhu, J., Sun, S.: Single-task and multitask sparse Gaussian processes. In: Proceedings of the International Conference on Machine Learning and Cybernetics, pp. 1033–1038. IEEE, New York (2013)Google Scholar
- 11.Sun, S.: Infinite mixtures of multivariate Gaussian processes. In: Proceedings of the International Conference on Machine Learning and Cybernetics, pp. 1011–1016. IEEE, New York (2013)Google Scholar
- 12.Luo, C., Sun, S.: Variational mixtures of Gaussian processes for classification. In: Proceedings of 26th International Joint Conference on Artificial Intelligence, pp. 4603–4609. Morgan Kaufmann, San Francisco (2017)Google Scholar
- 14.Wilson, A.G., Knowles, D.A., Ghahramani, Z.: Gaussian process regression networks. In: Proceedings of the 29th International Conference on Machine Learning, pp. 599–606. ACM, New York (2012)Google Scholar
- 15.Damianou, A., Lawrence, N.: Deep Gaussian processes. In: International Conference on Artificial Intelligence and Statistics, pp. 207–215. JMLR, Cambridge (2013)Google Scholar
- 17.Rasmussen, C.E., Ghahramani, Z.: Infinite mixtures of Gaussian process experts. Adv. Neural Inf. Process. Syst. 14(4), 881–888 (2002)Google Scholar
- 18.Meeds, E., Osindero, S.: An alternative infinite mixture of Gaussian process experts. Adv. Neural Inf. Process. Syst. 18(1), 883–890 (2006)Google Scholar