Price Prediction of Used Cars Using Machine Learning Techniques

The used-car market in India has grown rapidly due to rising affordability, greater digital accessibility, and increasing consumer demand, making accurate pricing predictions essential for fair and transparent valuation. This study proposes a data-driven framework for forecasting used car prices using machine learning (ML) techniques. The dataset, collected via web scraping from Cars24.com, includes listings from major Indian cities and key vehicle attributes such as manufacturing year, kilometres driven, fuel type, transmission type, and brand. Five ML algorithms, Linear Regression, Decision Tree, Random Forest, Gradient Boosting, and AdaBoost, were trained and evaluated to identify the most effective model. Among them, the Random Forest Regressor achieved the best performance with an R² score of 92.04% and a Mean Absolute Error (MAE) of 2.87%, demonstrating strong capability in capturing complex non-linear patterns. Machine learning, a core component of Artificial Intelligence, enables systems to learn autonomously from data and is widely applied across domains requiring predictive analysis. In the automotive sector, ML offers an objective and scalable approach to estimating resa