Abstract
This study investigates the use of machine learning techniques to predict car prices in the secondary market. Utilizing a comprehensive dataset of used car listings from the United Kingdom, we applied advanced machine learning models, including Random Forest and Neural Networks, to understand the factors influencing car prices and to develop accurate predictive models. Our analysis identified engine size and registration year as key determinants of car prices. The Neural Network model provided highly accurate predictions, closely matching actual prices in the majority of cases. Visual representations of feature importance and prediction errors further elucidate the model's effectiveness. This research demonstrates that machine learning can significantly enhance the accuracy of price predictions in the used car market, offering valuable insights for consumers, dealers, and policymakers. By leveraging these predictive models, stakeholders can make more informed decisions, optimize pricing strategies, and better understand market dynamics.