This thorough study looks at the use of machine learning (ML) techniques to forecast energy usage in buildings, with an emphasis on mosques. As energy use has a greater impact on both the environment and the economy, it is becoming increasingly important to optimize energy usage in buildings, especially for religious organizations such as mosques. The study goes into a variety of ML methods and models, including neural networks, regression models, decision trees, and clustering algorithms, each customized to a distinct difficulty in energy management. The paper evaluates the efficacy of several ML techniques, noting their merits, shortcomings, and potential applications. Additionally, it investigates the impact of climate, mosque design, occupancy patterns, and geographical variables on energy use. To achieve accurate energy consumption projections, rigorous data collecting, pre-processing, and model validation procedures are required. The paper also discusses important data sources and methodologies for mosque-specific energy analysis. Furthermore, the study emphasizes the practical benefits of applying ML in energy prediction, such as cost savings, increased environmental sustainability, and better resource allocation. This study’s ramifications extend beyond mosques, providing useful insights into energy management in buildings in general. By summarizing the current state of ML applications in mosque energy prediction, this study is an important resource for researchers, decision-makers, and energy management practitioners, paving the way for future advancements and the adoption of more sustainable energy practices in religious institutions.