With the growing concern for environmental sustainability and the transition towards greener technologies, the demand for electric vehicles (EVs), including Plugin Hybrid Electric Vehicles (PHEVs) and Battery Electric Vehicles (BEVs), has been steadily increasing. To address this demand effectively, it is crucial for manufacturing companies to accurately forecast the required quantity of EVs, specifically PHEVs and BEVs, in specific regions. This research employs data science methodologies, particularly machine learning algorithms, to analyze Electric Vehicle Population Datasets and determine the optimal approach for predicting the demand for PHEVs and BEVs. Through the utilization of various algorithms. this study aims to identify the most accurate model for forecasting the demand for PHEVs and BEVs in different geographic areas. The findings of this research will provide valuable insights for manufacturing companies, enabling them to make informed decisions regarding the quantity of PHEVs and BEVs to manufacture in particular areas. By aligning production quantities with regional demand, manufacturers can contribute to the advancement of sustainable transportation initiatives and meet the evolving needs of consumers in today's environmentally conscious society.