Predictive Modeling for Enhancing MOOC Completion Rates: A Case Study
DOI:
https://doi.org/10.34190/ecel.23.1.2792Keywords:
online asynchronous learning, predictive models, course completion time, MOOC analytics, deep learning in education, educational data miningAbstract
In the realm of online asynchronous learning platforms, accurately tracking student performance to predict
course completion times poses a significant challenge. Completion rates for MOOCs are typically low, with a
bias towards participants with higher education levels. Understanding factors such as student motivation,
engagement, participation, and learning pathway design is crucial for improving student outcomes in online
courses. This research developed a predictive framework utilizing advanced deep learning techniques to
accurately forecast course completion times for participants enrolled in an introductory programming course
("Python for Beginners" course on the Open Learning Platform of University of Moratuwa Sri Lanka). By
accurately tracking student performance and leveraging a diverse dataset encompassing demographic and
educational variables, the research seeks to identify factors influencing course completion and predict
individual student outcomes. By utilising deep learning techniques, the prediction performance of the model
will be improved, ultimately contributing to a more precise forecast of course completion times for
participants. Evaluation of the model resulted in low Mean Absolute Error (MAE) of 0.0080 and low Mean
Squared Error (MSE) of 0.0033 which promises the effectiveness of the developed method in accurately
predicting course completion times for students. The findings of this study may help increase the successful
completion rate of such courses which are delivered in the online asynchronous mode. The study employed
advanced deep learning models optimized through Bayesian methods, highlighting the potential of these
techniques to enhance MOOC completion rates by offering precise forecasts and actionable insights into
student engagement. The comprehensive analysis revealed that variables such as 'Current_Lesson', 'Session
Time Category', and 'District_Score' significantly influence completion times. The robust methodological
framework, including feature engineering, model training, and hyperparameter optimization, sets a precedent
for future research in the field. This research contributes to educational data mining and predictive analytics,
offering a scalable approach to improving completion rates and educational outcomes across various online
learning platforms. Future research should explore incorporating real-time data and longitudinal studies to
enhance model accuracy and generalizability. Additionally, addressing potential biases in the dataset, such as
demographic, prior knowledge, and resource access disparities, is essential to ensure the fair and equitable
application of the model across diverse student populations. Expanding the research to include a wider range
of courses and institutions will further validate the model's robustness and applicability in different
educational contexts.