Used Car Price Prediction Using Machine Learning

Predicting the resale price of used cars is a critical problem in the
automotive industry, affecting buyers, sellers, and online
marketplaces. This study presents a machine learning-based
approach to predict the resale price of used cars in India using
features such as brand, manufacturing year, kilometers driven,
fuel type, transmission, and number of previous owners. Two
regression algorithms are compared: Linear Regression and
Random Forest Regressor. The dataset comprises 200 records
generated based on realistic Indian used car market price ranges.
The models are evaluated using standard metrics including R²
Score, Mean Absolute Error (MAE), Root Mean Squared Error
(RMSE), and prediction accuracy. Experimental results
demonstrate that Random Forest Regressor achieves a superior
accuracy of 95.42% (R² = 0.9542) compared to Linear Regression
at 89.18% (R² = 0.8918), owing to its ability to capture non-linear
relationships such as depreciation curves and brand-specific
pricing. The proposed system provides a reliable, data-driven
framework for resale price estimation that can assist buyers,
sellers, and dealers in making informed decisions.