DATA-DRIVEN INSIGHTS INTO ELECTRIC VEHICLE ADOPTION FOR ENHANCING SUSTAINABLE TRANSPORT POLICY AND URBAN PLANNING

The growing urgency of climate change and environmental degradation has accelerated the global transition toward sustainable mobility solutions, with electric vehicles (EVs) emerging as a pivotal element in reducing carbon emissions and fostering environmentally friendly urban transportation systems. This study, titled "Driven Analysis of Electric Vehicle Population Trends for Sustainable Transportation Policies and Planning", presents a comprehensive, data-driven approach to understanding EV adoption patterns, forecasting future growth, and informing effective policy development.Initially, a Ridge Classifier is employed as the baseline model due to its robustness against multicollinearity and its capacity to manage high-dimensional data. While relatively simple, the Ridge Classifier provides a solid benchmark for classification tasks such as segmenting EV types or predicting growth categories.To enhance predictive performance, a Gradient Boosting Classifier is proposed and implemented as the advanced model. Gradient Boosting, an ensemble learning technique, builds a series of weak learners sequentially to construct a strong predictive model, thereby significantly improving accuracy and generalization performance.A comparative analysis between the Ridge and Gradient Boosting classifiers—evaluated using metrics such as accuracy, precision, recall, and F1-score—demonstrates a notable improvement in classification performance with the proposed model. These findings not only underscore the effectiveness of machine learning techniques in forecasting electric vehicle trends but also offer actionable insights for policymakers and urban planners.By identifying regions with slower EV adoption and evaluating the influence of infrastructure support and policy incentives, this study contributes to data-driven decision-making aimed at promoting sustainable transportation systems