<p>E-learning platforms have evolved as a highly successful means of learning, with recommender systems functioning as useful tools for assisting users in selecting the most appropriate courses. MOOCs (Massive Open Online Resources) have drifted the traditional teaching-learning approach from chalk-duster to the digital platform. MOOCs (Massive Open Online Resources) boosts the personalized learning by customize learning and suggesting e-content depending on the user’s preferences, interests, and search history. The purpose of this study is to discover and predict the parameters influencing the success of MOOCs (Massive Open Online Resources). These parameters depict the relationship between the factors stating the effectiveness of MOOCs (Massive Open Online Resources) known as EMOOCs. In this paper, the objective of the research objective is to propose the recommender model predicting the performance metrics of the study. To achieve the research objectives the following tasks are performed: a) Exploring the factors influencing the MOOCs (Massive Open Online Resources) b) By evaluating RMSE and MSE values to investigate the relationship between the parameters affecting the effectiveness of MOOCs (EMOOCs) c) To predict the performance metrics various Machine Learning Algorithms are implemented. d) Furthermore, the performance metrics values recommend the best algorithm for building the Recommender model e) Finally, to test and validate the results of the models- Structural Equation Modeling (SEM) is formulated using the Partial Least Squares (PLS) Smart-PLS 4 Software.</p>