One of the many impacts of the COVID-19 pandemic has been the increasing prevalence and accessibility of online education. This trend has also introduced challenges for students, instructors, and institutions. This study examines factors affecting online course satisfaction, focusing on individual, instructor, and institutional level characteristics with clustered, separated train and test datasets across two terms. This study compares Hierarchical Linear Model (HLM), Non-clustered and Clustered Random Forest (RF & MERF) models to understand these impacts. This intention is to provide a comprehensive framework comparing traditional HLM with the latest developed MERF models while delving into the effectiveness of RF and MERF models in predicting student satisfaction across different programs. This study investigates how MERF can be applied to analyzing real clustered higher education data to bridge the knowledge gap when evaluating different predictive models. The author encourages researchers to adopt an integrated approach combining HLM, RF, and MERF models with a suitable clustered dataset, as each model holds a unique niche in terms of their predictive performance, model sensitivity, and computational efficiency. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]