The growing adoption of electric vehicles (EVs) is crucial for reducing greenhouse gas emissions and promoting sustainable transportation. However, this rapid growth presents challenges such as managing charging demand, maintaining grid stability, and optimizing charging station usage. This study examines EV charging behavior within a potential local energy community in France, using data collected from September 2021 to August 2023 from 23 charging terminals at four universities. The analysis identifies patterns in charging times, session durations, and energy consumption, revealing trends and inefficiencies that impact the power grid’s overall stability. To improve energy planning and efficiency, three machine learning models were applied to forecast day-ahead EV charging demand. Among all the models, the Gradient Boosting model delivered the best performance, achieving the lowest error rates and the highest R2 value (0.664). This indicates that the model explains 66.4% of the variance in charge demand, highlighting the potential of advanced forecasting techniques to optimize energy management systems and enhance the reliability of electricity distribution. The analysis enables the prediction of electric vehicle demand, which can later be used to improve energy management at different scales, reducing costs and environmental impacts.