A carregar...
Publicação
Predicting student churn in subscription EdTech
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 2.03 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
Subscription-based educational technology (EdTech) companies experience significant revenue loss from student churn, making retention vital. Retaining engaged learners is generally more cost-effective than acquiring new ones. This study develops a predictive churn model using anonymised student data from an EdTech platform for children’s English learning. Following a CRISP-DM process, student activity, engagement, and financial features were engineered across multiple time windows to capture evolving student behaviours. Four machine learning algorithms-logistic regression, random forest, neural networks, and XGBoost (XGB)—were trained and compared. The optimised XGB model achieved the best performance, with approximately 0.84 accuracy, 0.63 F1 score, 0.85 recall, and the area under the curve (AUC) of 0.85 on test data, effectively identifying likely churners. Shapley Additive exPlanations (SHAP) based analysis revealed that engagement metrics, particularly the number of paid classes (both current and mean over 8 weeks), total learning time, engagement at gamified features, and student tenure, were the most influential predictors, confirming that highly engaged students are less likely to churn. This interpretable model provides actionable insights for retention strategies by predicting individual churn risk and highlighting key engagement drivers. In practice, even a 1% monthly reduction in churn could translate into multi-million-dollar annual savings for subscription EdTech providers. Overall, this research extends churn prediction into the EdTech domain, demonstrates the value of long-term engagement features, and applies explainable AI to enhance model transparency, thereby supporting its practical adoption.
Descrição
Gavrilova, L., & António, N. (2026). Predicting student churn in subscription EdTech: explainable machine learning for improving retention. Educational Technology Research and Development. https://doi.org/10.1007/s11423-026-10695-y
Palavras-chave
Customer churn prediction Machine learning Educational technology Subscription business model Education SDG 4 - Quality Education SDG 8 - Decent Work and Economic Growth