International Research Journal of Education and Technology

This paper explores the integration of advanced AI technologies for the dual objectives of car damage detection and price prediction in the automotive industry. Leveraging the YOLOv8 model, the system achieves high-accuracy detection of car damages through image analysis, while a Random Forest regressor predicts the market value of used cars based on numerical and textual features. By combining multimodal data—numerical, textual, and image-based inputs—the system provides comprehensive and reliable evaluations for users, enhancing transparency and decision-making in vehicle transactions. The project also addresses practical challenges such as scalability, accessibility, and the seamless integration of machine learning models into a user-friendly web application built using Flask. While the system offers significant benefits by automating routine vehicle assessments, it also emphasizes the importance of accurate model predictions, ethical use, and the inclusion of human oversight in critical decision-making processes. This approach has the potential to transform the car resale market, providing scalable, efficient, and user-centric solutions for both buyers and sellers.

Keywords – AI in Automotive, YOLOv8, Random Forest Regression, Multimodal Analysis, Car Damage Detection, Price Prediction, Machine Learning Integration.