Prediction and classification of churners in online learning using ensemble of distributed iterative classifiers
by V. Senthil Kumaran
International Journal of Learning Technology (IJLT), Vol. 17, No. 4, 2022

Abstract: In e-learning domain, the weak learners known as churn are the one who underperform and might drop from the course. Identifying and giving more attentions to such churn is an active research problem. Numerous methods have been proposed in the literature, which predicts churn based on their personal attributes and learning curve. One major limitation with the existing method is that they evaluate their system with minimal set of data. To overcome that issue and to improve the accuracy, this research work proposed a distributed iterative classifier that deploys an ensemble learning algorithm to generalise the model for predicting potential churn from personal attributes. Predictions from the base classifier are obtained using a distributed iterative classification algorithm that deploys a map-reduce framework. Iterative classification algorithm predicts signs of attrition in the learners through their online interactions. It can also process a very large network, which was lacking in the existing solution. The proposed system is validated using the features of five students and results are reported. Experimental results show that the proposed ensemble classifier predicts churn competently.

Online publication date: Mon, 20-Feb-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Learning Technology (IJLT):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com