The Indian automobile retail sector continues to face structural challenges in balancing demand fluctuations with inventory management. Passenger vehicles, particularly petrol light motor vehicles (LMVs), dominate the current market, while diesel vehicles are witnessing a steady decline due to policy restrictions and reduced consumer preference. This paper presents a data-driven framework for inventory optimization and demand forecasting in the automotive supply chain, developed as a case study from India. Using datasets from the Federation of Automobile Dealers Associations (FADA), VAHAN registration records, and regional RTO-level data covering FY 2022–2025, the study analyzes major passenger vehicle manufacturers—Maruti Suzuki, Tata Motors, Hyundai, and Kia. Forecasting techniques, including Gradient Boosting Regression (GBR), ARIMA, and Moving Average, are employed to predict demand trends, while Economic Order Quantity (EOQ) and safety stock models are applied to determine optimal inventory levels. Results indicate that actual inventory holdings remain consistently above optimal requirements, with average dealer stock levels of 50–55 days against an ideal benchmark of 30–35 days. By layering comparisons across India, Maharashtra, and the Vidarbha region, the study highlights how regional variations impact national inventory patterns and why Vidarbha serves as a critical case for balancing supply and demand. The proposed framework demonstrates potential cost reductions of 12–15% through optimized inventory planning and improved forecasting accuracy. The findings provide actionable insights for passenger vehicle dealers and OEMs and serve as a foundation for integrating inventory optimization with predictive supply chain orchestration models in future research.