The growing adoption of Electric Vehicles (EVs) is continuously leading to an increasing demand for reliable and accessible charging infrastructure. Ensuring the optimal distribution of EV charging stations is essential to support this transition, particularly in densely populated urban areas such as London. This study conducts an Exploratory Spatial Data Analysis (ESDA) of EV charging stations across London to understand their spatial distribution, density, and clustering patterns. Using spatial statistical methods and Machine Learning predictive models, developed by using clustering techniques such as K-Means, and Agglomerative Hierarchical Clustering (AHC), we identify areas of high concentration and potential gaps in infrastructure. The analysis reveals spatial disparities in station availability, highlighting underserved regions that could benefit from strategic infrastructure planning. Our findings provide data-driven insights to inform urban planners and policymakers in promoting equitable and efficient deployment of EV charging stations, thereby supporting the city’s sustainability and net-zero goals.