Several mobility vehicle rental companies have emerged owing to the increased preference for shared mobility as a short-distance transit option. These shared-mobility vehicles must be strategically placed at different locations to enable easy access to customers. However, without prior knowledge of the occurrence of rental demand, it becomes challenging for companies to respond quickly. In this study, we analyzed the factors affecting rental demand for shared electric mobility vehicles by utilizing actual data from the company EV PASS and predicted rental demand to ensure that the vehicles were distributed effectively, allowing customers to receive timely service. We compared the performance of machine learning models such as the Extra Trees regressor, CatBoost regressor, and LightGBM (Light Gradient Boosting Machine) models in predicting the demand for shared mobility vehicles. Additionally, we explored the use of an ensemble technique called voting regressor to reduce errors with an R2 score of 0.7629, it outperformed all the individual models. The analysis revealed that factors including humidity, precipitation, and solar radiation have a significant influence on rental demand. Based on the findings of this study, companies can effectively manage equipment and personnel, providing better shared electric mobility rental services, leading to increased customer satisfaction.