Car Price Prediction using Machine Learning Techniques

Accurate estimation of used car prices is pivotal in the automotive industry, influencing decisions for buyers, sellers, and financial institutions. Traditional valuation methods often rely on subjective assessments, leading to inconsistencies. This study introduces a data-driven approach employing machine learning techniques to predict used car prices with enhanced precision. Utilizing a comprehensive dataset encompassing various car attributes, we implemented and compared multiple regression models, including Linear Regression, Decision Tree, Random Forest, and XGBoost. The XGBoost Regressor outperformed others, achieving an R² score of 0.8630, indicating its robustness in capturing complex patterns within the data. To facilitate user interaction, the model was deployed through a Flask-based web application, featuring an intuitive interface for real-time price predictions. The integration of machine learning with web technologies offers a reliable tool for stakeholders, streamlining the car valuation process and promoting informed decision-making in the used car market.