Abstract

This research presents a data-driven framework for predicting quarterly EV demand, enabling automakers to navigate the transition from internal combustion engines to electric vehicles. By integrating multi-source analytics—including historical sales, stock price correlations, macroeconomic indicators, and charging infrastructure growth—we develop high-accuracy forecasting models that reduce prediction errors by 20% compared to traditional methods. The system incorporates real-time monitoring as of April 2025 to dynamically adjust for variables like lithium price swings and subsidy changes. A dual-layer governance mechanism ensures both analytical integrity and legal compliance ,Technical Governance and Regulatory Alignment.

Keywords