Student learning and how their lessons are delivered have been dramatically changed by COVID-19 pandemic, as evidenced by the widespread utilization of e-learning systems when the pandemic hit. However, the use of e-learning among students worldwide has not been as effective. The e-learning systems success model after the pandemic should be revised. This study examined the role of monitoring quality to validate the e-learning systems success using previous e-learning and information systems success models. Structural equation model was used in data analysis, involving data obtained from 800 students. Results demonstrated positive impacts of information quality, system quality and service quality, on user satisfaction, and positive impact of system use of user on student satisfaction and consequently on student loyalty. Monitoring quality did not show a positive impact on user satisfaction. Significant impact of user satisfaction on learning effectiveness was also shown. This study showed some significant implications for e-learning systems success models both in theory and in practice.

E-learning results from the integration of technology and education and has become an effective learning medium today. E-learning courses and systems with various services are on the rise owing to its importance. E-learning systems should be evaluated to assure successful delivery, effective usage, and positive impacts on learners. A holistic model that identifies various levels of success on a vast range of success determinants was proposed. The model was empirically validated using data obtained from 724 e-learning student users in Jordan. Structural Equation Modelling (SEM) was used in data analyses. Results showed that perceived usefulness of information systems, user training, system quality, and management support have positive effects on user’s behavioral intention; whereas perceived ease of use has not. Also, SEM displayed that user behavioral intention has a positive effect on information systems use, use on student satisfaction, and the latter on student loyalty. Machine Learning (ML) methods produce high correlation values reaching up to 80% in predicting Behavior Intention (BI) from the input factors, and student loyalty from student satisfaction factors. This indicates that the ML are promising techniques to forecast the future targets based on the input independent features.