Purchasing a used vehicle might be difficult. As with many other consumer items, the cost of a used automobile has increased dramatically in recent years. The unpleasant experience of being a car owner has also been exacerbated by growing interest rates and petrol prices. One of the major and fascinating fields of investigation is used automobile price prediction. As the number of automobiles on the road has increased significantly, more and more people are unable to purchase the newly manufactured vehicles due to a variety of factors, including excessive costs, limited supply, insufficient funds, and so on. As a result, the used automobile industry is expanding globally, although it is still in its infancy and is primarily controlled by the unorganized sector in Pakistan. Along with the outcomes of the experiments in this study. In order to predict the resale price of used cars given a number of parameters, such as the car's model, year of production, mark, selling type, fuel type, and current pricing, a variety of regression algorithms based on supervised machine learning were utilized in this study. Two key areas of the automotive domain vehicle price prediction and automobile recognition—are addressed by the Car Price prediction and recognition initiatives, the blends supervised machine learning with computer vision methods. The goal of this work is to equip users with the knowledge and skills necessary for making intelligent choices when buying cars and to identify cars through picture capture. In this study the main source of information for the forecasts is the Kaggle website. Random forest demonstrated a high degree of accuracy and a low root mean square error in all other investigated models. Our suggested model's performance demonstrates the usefulness and efficiency of the suggested investigation.