The University of Moratuwa in Sri Lanka created the open.uom.lk platform, an open learning environment that provides free asynchronous online courses in IT. The platform was created as a response to the expanding need for human capital in Sri Lanka’s IT sector, which is one of the few industries that has shown robust growth despite the country’s recent economic crisis. Over 270,000 students have registered in its flagship course, Trainee Full-Stack Developer, in the two years since it was released. Six subjects make up the course, which covers web design, Python programming, and a professional practice module with a capstone project. Like with many other MOOCs, completion rates are particularly low despite the large number of registrants. To address this, the research aims to create a binary classification model to predict course completion using student activity completion reports and demographic data on employment and educational background. Various machine learning algorithms, such as Logistic Regression, Random Forest, Decision Tree, Support Vector Machine, and Adaptive Boosting are utilized and compared. Cross-validation techniques, including stratified 10-fold cross-validation, are applied to avoid overfitting and handle class imbalance. Model performance is evaluated using Geometric Mean (GM), Matthews Correlation Coefficient (MCC), Cohen’s Kappa (κ), Precision, F1-Score, Recall, and Accuracy. This analysis aims to identify students at risk of not completing early on, enabling targeted interventions and course design improvements to increase completion rates. It also provides a framework for predicting course completion in other courses and the overall program.