A Machine Learning Framework for Automotive Price Prediction and Revenue Forecasting

Abstract: The automotive market’s increasing digitalization necessitates accurate, data-driven vehicle valuation models to en- hance market transparency and support strategic decision-making. This paper presents a machine learning framework designed to predict car prices based on a comprehensive set of technical and physical specifications. The core of this research is a comparative analysis of a baseline Linear Regression model against a more sophisticated Random Forest Regressor to evaluate their predictive efficacy. Using a structured dataset of over 200 vehicle records, our methodology incorporates a robust preprocessing pipeline, including one-hot encoding for categorical features and standard scaling for numerical attributes. The empirical results demonstrate the superior performance of the Random Forest model, which achieved a coefficient of determination (R2) of 0.96, alongside a Root Mean Squared Error (RMSE) of 1791.80 and a Mean Absolute Error (MAE) of 1251.66. Feature importance analysis reveals that engine size and horsepower are the most significant determinants of vehicle price. This framework serves as a foundational tool for broader business ap- plications, including the subsequent forecasting of sales volumes and revenue, thereby offering a scalable solution for stakeholders across the automotive industry.a

Keywords: Car Price Prediction, Machine Learning, Random Forest, Regression Analysis, Feature Importance, Automotive Analytics, Revenue Forecasting.