Time Series Forecasting of Electric Four-Wheeler Sales Using ARIMA: Implications for Sustainable Transportation Development

Abstract

The rapid growth of electric vehicle (EV) adoption has become a key component of sustainable transportation and environmental policy worldwide. Accurate forecasting of EV four-wheeler demand is essential for manufacturers, policymakers, and infrastructure planners to make informed decisions regarding production, charging infrastructure, and resource allocation. This study aims to analyze and forecast EV four-wheeler demand using both traditional time series techniques and modern machine learning approaches. Monthly EV four-wheeler sales data were collected and analyzed to identify underlying trends, seasonal patterns, and growth dynamics. Time series forecasting models, including Autoregressive Integrated Moving Average (ARIMA), were employed to model complex nonlinear relationships and improve forecasting accuracy. Model performance was evaluated using standard measures such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results indicate a significant upward trend in EV four-wheeler demand, driven by increasing environmental awareness, government incentives, and technological advancements. Comparative analysis demonstrates that machine learning models provide superior forecasting accuracy compared to conventional time series models when nonlinear patterns are present. The study offers valuable insights for strategic planning in the EV sector and contributes to the development of data-driven policies supporting sustainable mobility. The findings support the achievement of the United Nations Sustainable Development Goals, particularly SDG 7 (Affordable and Clean Energy), SDG 11 (Sustainable Cities and Communities), and SDG 13 (Climate Action), by facilitating informed decision-making for the expansion of electric vehicle ecosystems and the promotion of environmentally sustainable transportation.