The production of cars has been decreasing in most countries since the COVID-19 pandemic from 2020 to 2021. Due to this, the used car market has grown to be a booming industry by itself. Recent advances in online portals and platforms have made it possible to get more information about the factors that determine used car values. Hence, car price prediction has become a high-interest field of research. This paper aims to investigate the power of machine learning to build a model that will be able to predict the approximate price of a used car by utilizing the "Saudi Arabia Used Cars" Dataset which is collected from the Syarah platform and available on the Kaggle platform. The model assists both customer and seller to estimate the approximate price of a used car in the market. Three different Machine learning techniques were utilized which are Linear Regression, Random Forest, and XGBoost which score an MSE of 0.15, 0.10, and 0.19 respectively. The Random Forest Regressor algorithm outperformed other algorithms where it achieves the best result on the three evaluated metrics RMSE, MSE, and R-squared.

No abstract