Churn Prediction Task in MOOC
Journal of Computer Science Research · 2019
DOI: 10.30564/jcsr.v1i1.537 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science Research, 2019. Verfasst von Lisitsyna Liubov und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Churn prediction is a common task for machine learning applications in business. In this paper, this task is adapted for solving problem of low efficiency of massive open online courses (only 5% of all the students finish their course). The approach is presented on course “Methods and algorithms of the graph theory” held on national platform of online education in Russia. This paper includes all the steps to build an intelligent system to predict students who are active during the course, but not likely to finish it. The first part consists of constructing the right sample for prediction, EDA and choosing the most appropriate week of the course to make predictions on. The second part is about choosing the right metric and building models. Also, approach with using ensembles like stacking is proposed to increase the accuracy of predictions. As a result, a general approach to build a churn prediction model for online course is reviewed. This approach can be used for making the process of online education adaptive and intelligent for a separate student.
Zitieren
APA
Liubov, L., & A., O. S. (2019). Churn Prediction Task in MOOC. Journal of Computer Science Research. https://doi.org/10.30564/jcsr.v1i1.537
Vancouver
Liubov L, A. OS. Churn Prediction Task in MOOC. Journal of Computer Science Research. 2019. doi:10.30564/jcsr.v1i1.537
BibTeX
@article{Liubov2019,
author = {Liubov, Lisitsyna and A., Oreshin S.},
title = {Churn Prediction Task in MOOC},
journal = {Journal of Computer Science Research},
year = {2019},
doi = {10.30564/jcsr.v1i1.537}
}
EUVIMED