Application of Machine Learning and Predictive Algorithms in Student Contentment in Online Learning

This study uses cutting-edge machine learning approaches to forecast how students perform and how they feel in online learning settings. The investigation creates predictive algorithms that categorize students into achievement and fulfilment groups by combining engaging data-such as session length, activity count, and keystrokes-with satisfaction poll answers. While K-nearest neighbour and support vector regression are utilized to model satisfaction prediction, a variety of machine learning methods, such as random forest, gradient boosting, and elastic net regression, are employed to evaluate performance prediction. Strong relationships between engagement measures and academic outcomes, as well as among satisfaction components and student satisfaction, are found when the models are assessed using cross-validation along with performance metrics with accuracy, Fl-score, and MAE. In the rapidly changing world of online education, the technique provides teachers and educational organizations with useful tools to maximize online educational experiences and promote student accomplishment.