Student Satisfaction and Churn Predicting using Machine Learning Algorithms for EdTech course

Abstract

EdTech courses are believed to provide industry-oriented practical skills to the students to bridge the gap between academics and the industry. They also provide supporting education to the students to crack competitive exams in various sectors. With education institutions being shut down due to lockdown and moved to online mode, many students enrolled themselves in EdTech courses online creating competition amongst EdTech organizations. Reduced prices at times lead to reduced quality of the course content and the delivery. Students are often the prey in the competition who are left unsatisfied with the course and would never return to the organization for further courses leading to a churn. At least 50% of college students enroll in online courses in India but the completion rate is only about 13% which is very low. Customer churn is a major challenge to an organization reducing their growth as well as revenue. Two different machine learning algorithms viz. K-Nearest Neighbor (KNN) and Support Vector Machines (SVM) are proposed in this paper to predict the churn rate of students for EdTech courses based on the feedback of the students collected through the course end survey. The model also tells if the student is interested to enroll further in any other courses offered by the organization or refer the courses to their friends or relatives. The data is collected in real-time based on the online courses offered by a startup company and the churn rate for the organization is calculated.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 16 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.