Used Car Price Prediction using Machine Learning: A Case Study
Mustapha Hankar, Marouane Birjali, Abderrahim Beni‐Hssane
Abstract
In many business fields that are related to statistics and machine learning (ML), multiple linear regression (MLR) models are often used to estimate and fit a linear relationship between a continuous response variable and other explanatory variables. In our case study, we applied several regression techniques based on supervised machine learning to predict the resale price of used cars given many factors such as mileage, fuel type, fiscal power, mark, model, and the production year of the car. In all tested models, gradient boosting regressor showed a high R-squared score and low root mean square error.
Topics & Concepts
Gradient boostingBoosting (machine learning)Linear regressionRegressionRegression analysisMean squared errorMachine learningArtificial intelligenceComputer scienceExplanatory powerVariable (mathematics)Supervised learningStatisticsEconometricsMathematicsRandom forestArtificial neural networkEpistemologyPhilosophyMathematical analysisEnergy, Environment, and Transportation PoliciesForecasting Techniques and ApplicationsEnergy Load and Power Forecasting