Forecasting Mid‐ and Long‐Term Electric Vehicle Ownership Considering Social Network Effects

In the context of the global ‘dual carbon’ strategy, the rapid proliferation of electric vehicles (EVs) necessitates accurate medium‐ and long‐term stock forecasting. Such predictions are fundamental for formulating energy transition policies, planning power grid evolution, and deploying charging infrastructure. However, existing research predominantly focuses on short‐term forecasts, often neglecting the crucial influence of social networks on consumer adoption behavior. To address this lacuna, this study proposes an enhanced forecasting methodology based on a dynamic Bass diffusion model. We innovate by integrating a social network effect factor that simulates the interpersonal information dissemination process, thereby capturing a key driver of market penetration more effectively than the traditional model. An empirical analysis using historical EV ownership data from Beijing was conducted to validate the model. The results demonstrate that our enhanced model exhibits superior accuracy and stability in capturing the mid‐ and long‐term growth trajectory of the EV market. This research provides a robust analytical tool that offers critical support for strategic policymaking and the rational planning of charging infrastructure to accommodate the accelerated transition to electromobility.